Neural Configuration-Space Barriers for Manipulation Planning and Control

Kehan Long; Ki Myung Brian Lee; Melvin Leok; Nikola Raicevic; Nikolay Atanasov; Niyas Attasseri

arxiv: 2503.04929 · v4 · pith:EE3VNLBZnew · submitted 2025-03-06 · 💻 cs.RO · cs.LG· cs.SY· eess.SY

Neural Configuration-Space Barriers for Manipulation Planning and Control

Kehan Long , Ki Myung Brian Lee , Nikola Raicevic , Niyas Attasseri , Melvin Leok , Nikolay Atanasov This is my paper

Pith reviewed 2026-05-25 08:44 UTC · model grok-4.3

classification 💻 cs.RO cs.LGcs.SYeess.SY

keywords robot manipulationconfiguration spaceneural barriersmotion planningsafe controlpoint cloud observationsdistributionally robust optimization

0 comments

The pith

Neural configuration-space distance functions serve as barriers that let manipulators plan and control safely from point-cloud observations alone.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper shows how a learned configuration-space distance function can be turned into a barrier that certifies local collision-free regions around a robot arm. This barrier replaces most collision queries inside sampling-based planners, cutting computation time. A distributionally robust version of the same barrier is then used inside a control law so that approximation errors and sensor noise do not produce collisions. The approach is demonstrated on a six-degree-of-freedom arm in both simulation and hardware, operating in cluttered and moving scenes while using only onboard point clouds. If the method works as claimed, manipulators no longer need exact environment models or exhaustive collision checks at every step.

Core claim

A neural-network approximation of the configuration-space distance function defines a barrier certificate that certifies safety in the local free configuration space. This neural CDF barrier is inserted directly into sampling-based motion planners to reduce collision-checking operations and into a distributionally robust controller that accounts for modeling and sensing errors without assuming a known noise distribution.

What carries the argument

The neural CDF barrier, a neural-network approximation of the configuration-space distance function that is used to construct a barrier function certifying local collision-free configurations.

If this is right

Sampling-based planners require far fewer collision queries while still producing collision-free paths.
The resulting control law remains safe under approximation errors and point-cloud noise without extra safety margins.
Both planning and control operate from onboard point-cloud observations in cluttered and dynamic scenes.
The same CDF representation unifies the planning and control stages.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same barrier construction could be tested on robots with different kinematic structures if the CDF learner generalizes.
Warehouse or domestic robots might operate without pre-built maps once the method is shown to scale beyond the six-DOF arm.
Combining the barrier with online map building could further reduce dependence on perfect initial models.

Load-bearing premise

The learned neural CDF must accurately approximate the true local free configuration space and the distributionally robust formulation must cover all modeling errors and sensor noise.

What would settle it

A hardware trial on the xArm6 in which the robot, controlled by the neural CDF barrier and using only the supplied point-cloud data, collides with an obstacle visible in that point cloud.

Figures

Figures reproduced from arXiv: 2503.04929 by Kehan Long, Ki Myung Brian Lee, Melvin Leok, Nikola Raicevic, Nikolay Atanasov, Niyas Attasseri.

**Figure 2.** Figure 2: Snapshots of a 2-link arm navigating a dynamic environment with purple obstacles (velocity directions shown by arrows). The arm is tasked to follow the planned path in [PITH_FULL_IMAGE:figures/full_fig_p009_2.png] view at source ↗

**Figure 3.** Figure 3: Bubble-CDF planning for a 6-DoF xArm robot in a static environment, targeting an end-effector goal represented by a green sphere. (a) The initial configuration of the xArm. (b, c) Intermediate configurations illustrating the planned path as the robot avoids obstacles while progressing toward the goal. (d) The final goal configuration reached by the robot. (a) Start of Execution (b) Dynamic Obstacle Approac… view at source ↗

**Figure 4.** Figure 4: Snapshots of safe control execution on a 6-DoF xArm robot in an environment with dynamic obstacles. (a) The control execution begins at the initial configuration. (b) A dynamic obstacle (blue) approaches the robot from right. (c) The robot executes a defensive maneuver, moving upward to avoid the obstacle. (d) The robot successfully resumes tracking and reaches the goal configuration. Path lengths across a… view at source ↗

**Figure 5.** Figure 5: Bubble-CDF planner and DR-CBF control applied to two real-world setups for a 6-DoF xArm robot. The top row (a-d) represents Setup 1, with the robot navigating a cluttered environment featuring a combination of static and dynamic obstacles. Similarly, the bottom row (e-h) depicts Setup 2, showcasing the planner’s adaptability in a different obstacle layout. For both setups: (a, e) illustrate the bubble-CDF … view at source ↗

read the original abstract

Planning and control for high-dimensional robot manipulators in cluttered dynamic environments require computational efficiency and robust safety guarantees. Inspired by recent advances in learning configuration-space distance functions (CDFs) as representations of robot bodies, we propose a unified approach for motion planning and control that formulates safety constraints as CDF barriers. A CDF barrier approximates the local free configuration space, substantially reducing the number of collision-checking operations during motion planning. However, learning a CDF barrier with a neural network and relying on online sensor observations introduces uncertainties that must be considered during control synthesis. To address this, we develop a distributionally robust CDF barrier formulation for control that accounts for modeling errors and sensor noise without assuming a known underlying distribution. Simulations and hardware experiments on a UFactory xArm6 manipulator show that our neural CDF barrier formulation enables efficient planning and robust safe control in cluttered and dynamic environments, relying only on onboard point-cloud observations.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This paper turns learned CDFs into barriers for manipulator planning and control, with a distributional robustness layer to handle sensor and model uncertainty from point clouds.

read the letter

The main thing to know is that the authors formulate safety constraints directly from neural approximations of configuration-space distance functions, then add a distributionally robust control synthesis step that does not require knowing the underlying error distribution. They test the whole pipeline on an xArm6 in simulation and on hardware using only onboard point clouds in cluttered and dynamic scenes. This is a direct but incremental extension of recent CDF learning work, focused on cutting collision checks during planning while keeping the control law robust to the uncertainties that come with learned models and real sensors. The approach is sensible for high-dimensional arms where full collision checking is expensive. The hardware experiments are the right kind of evidence for the claims they make. The soft spots are mostly about the strength of the evidence rather than any internal contradiction. The abstract states that the method works but supplies no numbers on planning speedups, success rates, or how the robustness compares to simpler margins or baselines. That makes it hard to judge whether the distributional formulation actually delivers measurable gains or just works in the tested cases. The two load-bearing assumptions are that the neural CDF gives a good enough local free-space approximation and that the robust controller absorbs the remaining errors without extra tuning. Both are plausible for this setting, but they are empirical claims that reviewers will need to check against the full experiments and any ablations. This paper is for people working on learned safety constraints and motion planning for manipulators. A reader already following CDF or barrier methods would get the most out of it. It is coherent on its own terms and grounded enough in existing techniques that it should go to peer review rather than a desk reject.

Referee Report

1 major / 0 minor

Summary. The paper proposes neural configuration-space distance function (CDF) barriers for motion planning and control of high-dimensional manipulators. A learned neural CDF approximates the local free configuration space to reduce collision checks during planning. A distributionally robust CDF barrier formulation is developed for control synthesis to account for modeling errors and sensor noise without assuming a known distribution. The approach is evaluated via simulations and hardware experiments on a UFactory xArm6 manipulator using only onboard point-cloud observations in cluttered and dynamic environments.

Significance. If the empirical results hold with quantitative support, the work could provide a practical bridge between learned configuration-space representations and robust safety constraints for robotic manipulation, potentially improving efficiency in planning while maintaining safety guarantees under uncertainty. The hardware validation on a 6-DoF arm with real sensor data is a positive aspect.

major comments (1)

[Abstract] Abstract: The claims of 'efficient planning and robust safe control' rest on simulations and hardware experiments, but the text provides no quantitative results, error bars, success rates, timing metrics, or details on uncertainty handling, preventing verification of the central empirical claims.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback and positive remarks on the hardware validation and potential bridge between learned representations and robust safety. We address the single major comment below.

read point-by-point responses

Referee: [Abstract] Abstract: The claims of 'efficient planning and robust safe control' rest on simulations and hardware experiments, but the text provides no quantitative results, error bars, success rates, timing metrics, or details on uncertainty handling, preventing verification of the central empirical claims.

Authors: We agree that the abstract would be strengthened by including quantitative metrics to support the central claims. The full manuscript (Sections V and VI) reports detailed results from simulations and hardware experiments on the xArm6, including timing metrics, success rates, collision-check reductions, and analysis of the distributionally robust formulation for uncertainty. We will revise the abstract to incorporate key quantitative highlights (e.g., planning efficiency gains and robust control performance) while remaining within length limits. revision: yes

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The abstract and available text present an empirical approach: neural CDF barriers are learned from point clouds to approximate free configuration space, then used in a distributionally robust formulation for planning/control, validated via xArm6 simulations and hardware. No equations, self-definitions, fitted inputs renamed as predictions, or self-citation chains are quoted that reduce the central claim to its inputs by construction. Claims rest on experimental outcomes rather than internal reductions, satisfying the default expectation of no circularity (score 0-2).

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review; no explicit free parameters, axioms, or invented entities can be extracted from the provided text.

pith-pipeline@v0.9.0 · 5709 in / 1045 out tokens · 25008 ms · 2026-05-25T08:44:01.228581+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Reference graph

Works this paper leans on

47 extracted references · 47 canonical work pages · 2 internal anchors

[1]

Path planning for robotic manipulators using expanded bubbles of free c- space

Adnan Ademovic and Bakir Lacevic. Path planning for robotic manipulators using expanded bubbles of free c- space. In IEEE International Conference on Robotics and Automation (ICRA) , pages 77–82, 2016. doi: 10. 1109/ICRA.2016.7487118. 2

work page arXiv 2016
[2]

Control barrier function based quadratic programs for safety critical systems

Aaron D Ames, Xiangru Xu, Jessy W Grizzle, and Paulo Tabuada. Control barrier function based quadratic programs for safety critical systems. IEEE Transactions on Automatic Control , 62(8):3861–3876, 2017. 6

work page 2017
[3]

Ames, Samuel Coogan, Magnus Egerst- edt, Gennaro Notomista, Koushil Sreenath, and Paulo Tabuada

Aaron D. Ames, Samuel Coogan, Magnus Egerst- edt, Gennaro Notomista, Koushil Sreenath, and Paulo Tabuada. Control barrier functions: Theory and applica- tions. In 2019 18th European Control Conference (ECC), pages 3420–3431, 2019. 6

work page 2019
[4]

CasADi – A software framework for nonlinear optimization and optimal con- trol

Joel A E Andersson, Joris Gillis, Greg Horn, James B Rawlings, and Moritz Diehl. CasADi – A software framework for nonlinear optimization and optimal con- trol. Mathematical Programming Computation , 11(1): 1–36, 2019. doi: 10.1007/s12532-018-0139-4. 8

work page doi:10.1007/s12532-018-0139-4 2019
[5]

Efficient collision checking in sampling- based motion planning via safety certificates

Joshua Bialkowski, Michael Otte, Sertac Karaman, and Emilio Frazzoli. Efficient collision checking in sampling- based motion planning via safety certificates. The Inter- national Journal of Robotics Research , 35(7):767–796,

work page
[6]

Decomposition-based motion planning: A framework for real-time motion planning in high-dimensional configuration spaces

Oliver Brock and Lydia Kavraki. Decomposition-based motion planning: A framework for real-time motion planning in high-dimensional configuration spaces. In Proc. of IEEE International Conference on Robotics and Automation, volume 2, pages 1469–1474. IEEE, 2001. 2

work page 2001
[7]

Safe dynamic motion genera- tion in configuration space using differentiable distance fields

Xuemin Chi, Yiming Li, Jihao Huang, Bolun Dai, Zhitao Liu, and Sylvain Calinon. Safe dynamic motion genera- tion in configuration space using differentiable distance fields. arXiv preprint arXiv:2412.16456 , 2024. 1, 2, 8, 9, 10

work page arXiv 2024
[8]

Pybullet, a python module for physics simulation for games, robotics and machine learning

Erwin Coumans and Yunfei Bai. Pybullet, a python module for physics simulation for games, robotics and machine learning. http://pybullet.org, 2016–2021. 7, 9

work page 2016
[9]

Certified polyhedral de- compositions of collision-free configuration space

Hongkai Dai, Alexandre Amice, Peter Werner, Annan Zhang, and Russ Tedrake. Certified polyhedral de- compositions of collision-free configuration space. The International Journal of Robotics Research , 43(9):1322– 1341, 2024. doi: 10.1177/02783649231201437. 2

work page doi:10.1177/02783649231201437 2024
[10]

Invariant configuration-space bubbles for revolute serial-chain robots

Claus Danielson. Invariant configuration-space bubbles for revolute serial-chain robots. IEEE Control Systems Letters, 7:745–750, 2023. doi: 10.1109/LCSYS.2022. 3224685. 2

work page doi:10.1109/lcsys.2022 2023
[11]

Computing Large Convex Regions of Obstacle-Free Space Through Semidefinite Programming, pages 109–124

Robin Deits and Russ Tedrake. Computing Large Convex Regions of Obstacle-Free Space Through Semidefinite Programming, pages 109–124. Springer International Publishing, Cham, 2015. ISBN 978-3-319-16595-0. doi: 10.1007/978-3-319-16595-0 7. URL https://doi.org/10. 1007/978-3-319-16595-0 7. 2

work page doi:10.1007/978-3-319-16595-0 2015
[12]

Dijkstra

E W. Dijkstra. A note on two problems in connexion with graphs. Numerische Mathematik, 1:269–271, 1959. 5

work page 1959
[13]

Learning models as functionals of signed- distance fields for manipulation planning

Danny Driess, Jung-Su Ha, Marc Toussaint, and Russ Tedrake. Learning models as functionals of signed- distance fields for manipulation planning. In Conference on robot learning , pages 245–255. PMLR, 2022. 2

work page 2022
[14]

Data- driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations

Peyman Mohajerin Esfahani and Daniel Kuhn. Data- driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations. Mathematical Programming , 171:115– 166, 2018. 6

work page 2018
[15]

Dropout as a bayesian approximation: Representing model uncertainty in deep learning

Yarin Gal and Zoubin Ghahramani. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In International Conference on Machine Learning, volume 48, pages 1050–1059, 2016. 7

work page 2016
[16]

Explicit refer- ence governor for constrained nonlinear systems

Emanuele Garone and Marco M Nicotra. Explicit refer- ence governor for constrained nonlinear systems. IEEE Transactions on Automatic Control , 61(5):1379–1384,

work page
[17]

Fi- esta: Fast incremental euclidean distance fields for online motion planning of aerial robots

Luxin Han, Fei Gao, Boyu Zhou, and Shaojie Shen. Fi- esta: Fast incremental euclidean distance fields for online motion planning of aerial robots. In 2019 IEEE/RSJ In- ternational Conference on Intelligent Robots and Systems (IROS), pages 4423–4430, 2019. 3

work page 2019
[18]

Hart, Nils J

Peter E. Hart, Nils J. Nilsson, and Bertram Raphael. A formal basis for the heuristic determination of minimum cost paths. IEEE Transactions on Systems Science and Cybernetics, 4(2):100–107, 1968. 5

work page 1968
[19]

Lazy collision checking in asymptotically- optimal motion planning

Kris Hauser. Lazy collision checking in asymptotically- optimal motion planning. In IEEE International Confer- ence on Robotics and Automation (ICRA) , pages 2951– 2957, 2015. 2, 4, 8

work page 2015
[20]

A broy- den—fletcher—goldfarb—shanno optimization proce- dure for molecular geometries

John D Head and Michael C Zerner. A broy- den—fletcher—goldfarb—shanno optimization proce- dure for molecular geometries. Chemical physics letters, 122(3):264–270, 1985. 3

work page 1985
[21]

Gaussian Error Linear Units (GELUs)

Dan Hendrycks and Kevin Gimpel. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 , 2016. 7

work page internal anchor Pith review Pith/arXiv arXiv 2016
[22]

PID control

Michael A Johnson and Mohammad H Moradi. PID control. Springer, 2005. 2

work page 2005
[23]

Probabilistic roadmaps for path planning in high-dimensional configuration spaces

Lydia E Kavraki, Petr Svestka, J-C Latombe, and Mark H Overmars. Probabilistic roadmaps for path planning in high-dimensional configuration spaces. IEEE Transac- tions on Robotics and Automation (T-RO) , 12(4):566– 580, 1996. 1, 2

work page 1996
[24]

Lidar-based online control barrier function synthesis for safe navigation in unknown envi- ronments

Shaghayegh Keyumarsi, Made Widhi Surya Atman, and Azwirman Gusrialdi. Lidar-based online control barrier function synthesis for safe navigation in unknown envi- ronments. IEEE Robotics and Automation Letters , 9(2): 1043–1050, 2024. 3

work page 2024
[25]

Neu- ral joint space implicit signed distance functions for reactive robot manipulator control

Mikhail Koptev, Nadia Figueroa, and Aude Billard. Neu- ral joint space implicit signed distance functions for reactive robot manipulator control. IEEE Robotics and Automation Letters , 8(2):480–487, 2023. doi: 10.1109/ LRA.2022.3227860. 1, 2, 3

work page arXiv 2023
[26]

Kuffner and S.M

J.J. Kuffner and S.M. LaValle. Rrt-connect: An efficient approach to single-query path planning. In Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Pro- ceedings (Cat. No.00CH37065) , volume 2, pages 995– 1001 vol.2, 2000. 2, 8

work page 2000
[27]

Rapidly- exploring random trees: Progress and prospects

Steven M LaValle and James J Kuffner. Rapidly- exploring random trees: Progress and prospects. Al- gorithmic and computational robotics , pages 303–307,

work page
[28]

Safe bubble cover for motion planning on distance fields

Ki Myung Brian Lee, Zhirui Dai, Cedric Le Gentil, Lan Wu, Nikolay Atanasov, and Teresa Vidal-Calleja. Safe bubble cover for motion planning on distance fields. arXiv preprint arXiv:2408.13377 , 2024. 2, 4, 5

work page arXiv 2024
[29]

Configuration space distance fields for manipu- lation planning

Yiming Li, Xuemin Chi, Amirreza Razmjoo, and Sylvain Calinon. Configuration space distance fields for manipu- lation planning. In Robotics: Science and Systems (RSS) ,

work page
[30]

Representing robot geometry as distance fields: Applications to whole-body manipulation

Yiming Li, Yan Zhang, Amirreza Razmjoo, and Sylvain Calinon. Representing robot geometry as distance fields: Applications to whole-body manipulation. In IEEE International Conference on Robotics and Automation (ICRA), pages 15351–15357, 2024. 1, 2, 3

work page 2024
[31]

Fast and safe path-following control using a state-dependent directional metric

Zhichao Li, ¨Om¨ur Arslan, and Nikolay Atanasov. Fast and safe path-following control using a state-dependent directional metric. In IEEE International Conference on Robotics and Automation (ICRA) , pages 6176–6182,

work page
[32]

Learning barrier functions with memory for robust safe navigation

Kehan Long, Cheng Qian, Jorge Cort ´es, and Nikolay Atanasov. Learning barrier functions with memory for robust safe navigation. IEEE Robotics and Automation Letters (RA-L), 6(3):4931–4938, 2021. 1, 3

work page 2021
[33]

Neu- ral configuration distance function for continuum robot control

Kehan Long, Hardik Parwana, Georgios Fainekos, Bardh Hoxha, Hideki Okamoto, and Nikolay Atanasov. Neu- ral configuration distance function for continuum robot control. arXiv preprint arXiv:2409.13865 , 2024. 3

work page arXiv 2024
[34]

Sensor-based distri- butionally robust control for safe robot navigation in dy- namic environments

Kehan Long, Yinzhuang Yi, Zhirui Dai, Sylvia Herbert, Jorge Cort´es, and Nikolay Atanasov. Sensor-based distri- butionally robust control for safe robot navigation in dy- namic environments. arXiv preprint arXiv:2405.18251 ,

work page arXiv
[35]

V oxblox: Incremental 3d Euclidean signed distance fields for on-board MA V planning

Helen Oleynikova, Zachary Taylor, Marius Fehr, Roland Siegwart, and Juan Nieto. V oxblox: Incremental 3d Euclidean signed distance fields for on-board MA V planning. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 1366–1373,

work page
[36]

DeepSDF: Learning continuous signed distance functions for shape represen- tation

Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, and Steven Lovegrove. DeepSDF: Learning continuous signed distance functions for shape represen- tation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 165–174, 2019. 1, 3

work page 2019
[37]

Carlos Quintero-Pe ˜na, Wil Thomason, Zachary Kingston, Anastasios Kyrillidis, and Lydia E. Kavraki. Stochastic implicit neural signed distance functions for safe motion planning under sensing uncertainty. In IEEE Interna- tional Conference on Robotics and Automation (ICRA) , pages 2360–2367, 2024. 1

work page 2024
[38]

Sample-Based Planning with Volumes in Configuration Space

Alexander Shkolnik and Russ Tedrake. Sample-based planning with volumes in configuration space. arXiv preprint arXiv:1109.3145, 2011. 2

work page internal anchor Pith review Pith/arXiv arXiv 2011
[39]

Molnar, Ryan Sinnet, and Aaron D

Andrew Singletary, William Guffey, Tamas G. Molnar, Ryan Sinnet, and Aaron D. Ames. Safety-critical manip- ulation for collision-free food preparation. IEEE Robotics and Automation Letters , 7(4):10954–10961, 2022. 1, 2

work page 2022
[40]

Implicit neural representations with periodic activation functions

Vincent Sitzmann, Julien Martel, Alexander Bergman, David Lindell, and Gordon Wetzstein. Implicit neural representations with periodic activation functions. In International Conference on Neural Information Process- ing Systems (NeurIPS) , volume 33, pages 7462–7473,

work page
[41]

S ¸ucan, Mark Moll, and Lydia E

Ioan A. S ¸ucan, Mark Moll, and Lydia E. Kavraki. The Open Motion Planning Library. IEEE Robotics & Au- tomation Magazine , 19(4):72–82, December 2012. doi: 10.1109/MRA.2012.2205651. https://ompl.kavrakilab. org. 8

work page doi:10.1109/mra.2012.2205651 2012
[42]

Ramp: Hierarchical reactive motion planning for manipulation tasks using implicit signed distance functions

Vasileios Vasilopoulos, Suveer Garg, Pedro Piacenza, Jinwook Huh, and V olkan Isler. Ramp: Hierarchical reactive motion planning for manipulation tasks using implicit signed distance functions. In IEEE/RSJ Inter- national Conference on Intelligent Robots and Systems (IROS), pages 10551–10558, 2023. 2

work page 2023
[43]

A method on dynamic path planning for robotic manipulator autonomous obstacle avoidance based on an improved RRT algorithm

Kun Wei and Bingyin Ren. A method on dynamic path planning for robotic manipulator autonomous obstacle avoidance based on an improved RRT algorithm. Sen- sors, 18(2):571, 2018. 1

work page 2018
[44]

Faster algorithms for growing collision-free convex polytopes in robot configuration space

Peter Werner, Thomas Cohn, Rebecca H Jiang, Tim Seyde, Max Simchowitz, Russ Tedrake, and Daniela Rus. Faster algorithms for growing collision-free convex polytopes in robot configuration space. arXiv preprint arXiv:2410.12649, 2024. 2

work page arXiv 2024
[45]

Libo Yang and S.M. LaValle. The sampling-based neighborhood graph: an approach to computing and executing feedback motion strategies. IEEE Transactions on Robotics and Automation , 20(3):419–432, 2004. doi: 10.1109/TRA.2004.824640. 2

work page doi:10.1109/tra.2004.824640 2004
[46]

Efficient motion planning for manipulators with control barrier function- induced neural controller

Mingxin Yu, Chenning Yu, M-Mahdi Naddaf-Sh, Devesh Upadhyay, Sicun Gao, and Chuchu Fan. Efficient motion planning for manipulators with control barrier function- induced neural controller. In 2024 IEEE International Conference on Robotics and Automation (ICRA) , pages 14348–14355, 2024. 2, 3

work page 2024
[47]

Efficient collision detection framework for enhancing collision-free robot motion

Xiankun Zhu, Yucheng Xin, Shoujie Li, Houde Liu, Chongkun Xia, and Bin Liang. Efficient collision detection framework for enhancing collision-free robot motion. arXiv preprint arXiv:2409.14955, 2024. 1, 2, 8, 9, 10

work page arXiv 2024

[1] [1]

Path planning for robotic manipulators using expanded bubbles of free c- space

Adnan Ademovic and Bakir Lacevic. Path planning for robotic manipulators using expanded bubbles of free c- space. In IEEE International Conference on Robotics and Automation (ICRA) , pages 77–82, 2016. doi: 10. 1109/ICRA.2016.7487118. 2

work page arXiv 2016

[2] [2]

Control barrier function based quadratic programs for safety critical systems

Aaron D Ames, Xiangru Xu, Jessy W Grizzle, and Paulo Tabuada. Control barrier function based quadratic programs for safety critical systems. IEEE Transactions on Automatic Control , 62(8):3861–3876, 2017. 6

work page 2017

[3] [3]

Ames, Samuel Coogan, Magnus Egerst- edt, Gennaro Notomista, Koushil Sreenath, and Paulo Tabuada

Aaron D. Ames, Samuel Coogan, Magnus Egerst- edt, Gennaro Notomista, Koushil Sreenath, and Paulo Tabuada. Control barrier functions: Theory and applica- tions. In 2019 18th European Control Conference (ECC), pages 3420–3431, 2019. 6

work page 2019

[4] [4]

CasADi – A software framework for nonlinear optimization and optimal con- trol

Joel A E Andersson, Joris Gillis, Greg Horn, James B Rawlings, and Moritz Diehl. CasADi – A software framework for nonlinear optimization and optimal con- trol. Mathematical Programming Computation , 11(1): 1–36, 2019. doi: 10.1007/s12532-018-0139-4. 8

work page doi:10.1007/s12532-018-0139-4 2019

[5] [5]

Efficient collision checking in sampling- based motion planning via safety certificates

Joshua Bialkowski, Michael Otte, Sertac Karaman, and Emilio Frazzoli. Efficient collision checking in sampling- based motion planning via safety certificates. The Inter- national Journal of Robotics Research , 35(7):767–796,

work page

[6] [6]

Decomposition-based motion planning: A framework for real-time motion planning in high-dimensional configuration spaces

Oliver Brock and Lydia Kavraki. Decomposition-based motion planning: A framework for real-time motion planning in high-dimensional configuration spaces. In Proc. of IEEE International Conference on Robotics and Automation, volume 2, pages 1469–1474. IEEE, 2001. 2

work page 2001

[7] [7]

Safe dynamic motion genera- tion in configuration space using differentiable distance fields

Xuemin Chi, Yiming Li, Jihao Huang, Bolun Dai, Zhitao Liu, and Sylvain Calinon. Safe dynamic motion genera- tion in configuration space using differentiable distance fields. arXiv preprint arXiv:2412.16456 , 2024. 1, 2, 8, 9, 10

work page arXiv 2024

[8] [8]

Pybullet, a python module for physics simulation for games, robotics and machine learning

Erwin Coumans and Yunfei Bai. Pybullet, a python module for physics simulation for games, robotics and machine learning. http://pybullet.org, 2016–2021. 7, 9

work page 2016

[9] [9]

Certified polyhedral de- compositions of collision-free configuration space

Hongkai Dai, Alexandre Amice, Peter Werner, Annan Zhang, and Russ Tedrake. Certified polyhedral de- compositions of collision-free configuration space. The International Journal of Robotics Research , 43(9):1322– 1341, 2024. doi: 10.1177/02783649231201437. 2

work page doi:10.1177/02783649231201437 2024

[10] [10]

Invariant configuration-space bubbles for revolute serial-chain robots

Claus Danielson. Invariant configuration-space bubbles for revolute serial-chain robots. IEEE Control Systems Letters, 7:745–750, 2023. doi: 10.1109/LCSYS.2022. 3224685. 2

work page doi:10.1109/lcsys.2022 2023

[11] [11]

Computing Large Convex Regions of Obstacle-Free Space Through Semidefinite Programming, pages 109–124

Robin Deits and Russ Tedrake. Computing Large Convex Regions of Obstacle-Free Space Through Semidefinite Programming, pages 109–124. Springer International Publishing, Cham, 2015. ISBN 978-3-319-16595-0. doi: 10.1007/978-3-319-16595-0 7. URL https://doi.org/10. 1007/978-3-319-16595-0 7. 2

work page doi:10.1007/978-3-319-16595-0 2015

[12] [12]

Dijkstra

E W. Dijkstra. A note on two problems in connexion with graphs. Numerische Mathematik, 1:269–271, 1959. 5

work page 1959

[13] [13]

Learning models as functionals of signed- distance fields for manipulation planning

Danny Driess, Jung-Su Ha, Marc Toussaint, and Russ Tedrake. Learning models as functionals of signed- distance fields for manipulation planning. In Conference on robot learning , pages 245–255. PMLR, 2022. 2

work page 2022

[14] [14]

Data- driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations

Peyman Mohajerin Esfahani and Daniel Kuhn. Data- driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations. Mathematical Programming , 171:115– 166, 2018. 6

work page 2018

[15] [15]

Dropout as a bayesian approximation: Representing model uncertainty in deep learning

Yarin Gal and Zoubin Ghahramani. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In International Conference on Machine Learning, volume 48, pages 1050–1059, 2016. 7

work page 2016

[16] [16]

Explicit refer- ence governor for constrained nonlinear systems

Emanuele Garone and Marco M Nicotra. Explicit refer- ence governor for constrained nonlinear systems. IEEE Transactions on Automatic Control , 61(5):1379–1384,

work page

[17] [17]

Fi- esta: Fast incremental euclidean distance fields for online motion planning of aerial robots

Luxin Han, Fei Gao, Boyu Zhou, and Shaojie Shen. Fi- esta: Fast incremental euclidean distance fields for online motion planning of aerial robots. In 2019 IEEE/RSJ In- ternational Conference on Intelligent Robots and Systems (IROS), pages 4423–4430, 2019. 3

work page 2019

[18] [18]

Hart, Nils J

Peter E. Hart, Nils J. Nilsson, and Bertram Raphael. A formal basis for the heuristic determination of minimum cost paths. IEEE Transactions on Systems Science and Cybernetics, 4(2):100–107, 1968. 5

work page 1968

[19] [19]

Lazy collision checking in asymptotically- optimal motion planning

Kris Hauser. Lazy collision checking in asymptotically- optimal motion planning. In IEEE International Confer- ence on Robotics and Automation (ICRA) , pages 2951– 2957, 2015. 2, 4, 8

work page 2015

[20] [20]

A broy- den—fletcher—goldfarb—shanno optimization proce- dure for molecular geometries

John D Head and Michael C Zerner. A broy- den—fletcher—goldfarb—shanno optimization proce- dure for molecular geometries. Chemical physics letters, 122(3):264–270, 1985. 3

work page 1985

[21] [21]

Gaussian Error Linear Units (GELUs)

Dan Hendrycks and Kevin Gimpel. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 , 2016. 7

work page internal anchor Pith review Pith/arXiv arXiv 2016

[22] [22]

PID control

Michael A Johnson and Mohammad H Moradi. PID control. Springer, 2005. 2

work page 2005

[23] [23]

Probabilistic roadmaps for path planning in high-dimensional configuration spaces

Lydia E Kavraki, Petr Svestka, J-C Latombe, and Mark H Overmars. Probabilistic roadmaps for path planning in high-dimensional configuration spaces. IEEE Transac- tions on Robotics and Automation (T-RO) , 12(4):566– 580, 1996. 1, 2

work page 1996

[24] [24]

Lidar-based online control barrier function synthesis for safe navigation in unknown envi- ronments

Shaghayegh Keyumarsi, Made Widhi Surya Atman, and Azwirman Gusrialdi. Lidar-based online control barrier function synthesis for safe navigation in unknown envi- ronments. IEEE Robotics and Automation Letters , 9(2): 1043–1050, 2024. 3

work page 2024

[25] [25]

Neu- ral joint space implicit signed distance functions for reactive robot manipulator control

Mikhail Koptev, Nadia Figueroa, and Aude Billard. Neu- ral joint space implicit signed distance functions for reactive robot manipulator control. IEEE Robotics and Automation Letters , 8(2):480–487, 2023. doi: 10.1109/ LRA.2022.3227860. 1, 2, 3

work page arXiv 2023

[26] [26]

Kuffner and S.M

J.J. Kuffner and S.M. LaValle. Rrt-connect: An efficient approach to single-query path planning. In Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Pro- ceedings (Cat. No.00CH37065) , volume 2, pages 995– 1001 vol.2, 2000. 2, 8

work page 2000

[27] [27]

Rapidly- exploring random trees: Progress and prospects

Steven M LaValle and James J Kuffner. Rapidly- exploring random trees: Progress and prospects. Al- gorithmic and computational robotics , pages 303–307,

work page

[28] [28]

Safe bubble cover for motion planning on distance fields

Ki Myung Brian Lee, Zhirui Dai, Cedric Le Gentil, Lan Wu, Nikolay Atanasov, and Teresa Vidal-Calleja. Safe bubble cover for motion planning on distance fields. arXiv preprint arXiv:2408.13377 , 2024. 2, 4, 5

work page arXiv 2024

[29] [29]

Configuration space distance fields for manipu- lation planning

Yiming Li, Xuemin Chi, Amirreza Razmjoo, and Sylvain Calinon. Configuration space distance fields for manipu- lation planning. In Robotics: Science and Systems (RSS) ,

work page

[30] [30]

Representing robot geometry as distance fields: Applications to whole-body manipulation

Yiming Li, Yan Zhang, Amirreza Razmjoo, and Sylvain Calinon. Representing robot geometry as distance fields: Applications to whole-body manipulation. In IEEE International Conference on Robotics and Automation (ICRA), pages 15351–15357, 2024. 1, 2, 3

work page 2024

[31] [31]

Fast and safe path-following control using a state-dependent directional metric

Zhichao Li, ¨Om¨ur Arslan, and Nikolay Atanasov. Fast and safe path-following control using a state-dependent directional metric. In IEEE International Conference on Robotics and Automation (ICRA) , pages 6176–6182,

work page

[32] [32]

Learning barrier functions with memory for robust safe navigation

Kehan Long, Cheng Qian, Jorge Cort ´es, and Nikolay Atanasov. Learning barrier functions with memory for robust safe navigation. IEEE Robotics and Automation Letters (RA-L), 6(3):4931–4938, 2021. 1, 3

work page 2021

[33] [33]

Neu- ral configuration distance function for continuum robot control

Kehan Long, Hardik Parwana, Georgios Fainekos, Bardh Hoxha, Hideki Okamoto, and Nikolay Atanasov. Neu- ral configuration distance function for continuum robot control. arXiv preprint arXiv:2409.13865 , 2024. 3

work page arXiv 2024

[34] [34]

Sensor-based distri- butionally robust control for safe robot navigation in dy- namic environments

Kehan Long, Yinzhuang Yi, Zhirui Dai, Sylvia Herbert, Jorge Cort´es, and Nikolay Atanasov. Sensor-based distri- butionally robust control for safe robot navigation in dy- namic environments. arXiv preprint arXiv:2405.18251 ,

work page arXiv

[35] [35]

V oxblox: Incremental 3d Euclidean signed distance fields for on-board MA V planning

Helen Oleynikova, Zachary Taylor, Marius Fehr, Roland Siegwart, and Juan Nieto. V oxblox: Incremental 3d Euclidean signed distance fields for on-board MA V planning. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 1366–1373,

work page

[36] [36]

DeepSDF: Learning continuous signed distance functions for shape represen- tation

Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, and Steven Lovegrove. DeepSDF: Learning continuous signed distance functions for shape represen- tation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 165–174, 2019. 1, 3

work page 2019

[37] [37]

Carlos Quintero-Pe ˜na, Wil Thomason, Zachary Kingston, Anastasios Kyrillidis, and Lydia E. Kavraki. Stochastic implicit neural signed distance functions for safe motion planning under sensing uncertainty. In IEEE Interna- tional Conference on Robotics and Automation (ICRA) , pages 2360–2367, 2024. 1

work page 2024

[38] [38]

Sample-Based Planning with Volumes in Configuration Space

Alexander Shkolnik and Russ Tedrake. Sample-based planning with volumes in configuration space. arXiv preprint arXiv:1109.3145, 2011. 2

work page internal anchor Pith review Pith/arXiv arXiv 2011

[39] [39]

Molnar, Ryan Sinnet, and Aaron D

Andrew Singletary, William Guffey, Tamas G. Molnar, Ryan Sinnet, and Aaron D. Ames. Safety-critical manip- ulation for collision-free food preparation. IEEE Robotics and Automation Letters , 7(4):10954–10961, 2022. 1, 2

work page 2022

[40] [40]

Implicit neural representations with periodic activation functions

Vincent Sitzmann, Julien Martel, Alexander Bergman, David Lindell, and Gordon Wetzstein. Implicit neural representations with periodic activation functions. In International Conference on Neural Information Process- ing Systems (NeurIPS) , volume 33, pages 7462–7473,

work page

[41] [41]

S ¸ucan, Mark Moll, and Lydia E

Ioan A. S ¸ucan, Mark Moll, and Lydia E. Kavraki. The Open Motion Planning Library. IEEE Robotics & Au- tomation Magazine , 19(4):72–82, December 2012. doi: 10.1109/MRA.2012.2205651. https://ompl.kavrakilab. org. 8

work page doi:10.1109/mra.2012.2205651 2012

[42] [42]

Ramp: Hierarchical reactive motion planning for manipulation tasks using implicit signed distance functions

Vasileios Vasilopoulos, Suveer Garg, Pedro Piacenza, Jinwook Huh, and V olkan Isler. Ramp: Hierarchical reactive motion planning for manipulation tasks using implicit signed distance functions. In IEEE/RSJ Inter- national Conference on Intelligent Robots and Systems (IROS), pages 10551–10558, 2023. 2

work page 2023

[43] [43]

A method on dynamic path planning for robotic manipulator autonomous obstacle avoidance based on an improved RRT algorithm

Kun Wei and Bingyin Ren. A method on dynamic path planning for robotic manipulator autonomous obstacle avoidance based on an improved RRT algorithm. Sen- sors, 18(2):571, 2018. 1

work page 2018

[44] [44]

Faster algorithms for growing collision-free convex polytopes in robot configuration space

Peter Werner, Thomas Cohn, Rebecca H Jiang, Tim Seyde, Max Simchowitz, Russ Tedrake, and Daniela Rus. Faster algorithms for growing collision-free convex polytopes in robot configuration space. arXiv preprint arXiv:2410.12649, 2024. 2

work page arXiv 2024

[45] [45]

Libo Yang and S.M. LaValle. The sampling-based neighborhood graph: an approach to computing and executing feedback motion strategies. IEEE Transactions on Robotics and Automation , 20(3):419–432, 2004. doi: 10.1109/TRA.2004.824640. 2

work page doi:10.1109/tra.2004.824640 2004

[46] [46]

Efficient motion planning for manipulators with control barrier function- induced neural controller

Mingxin Yu, Chenning Yu, M-Mahdi Naddaf-Sh, Devesh Upadhyay, Sicun Gao, and Chuchu Fan. Efficient motion planning for manipulators with control barrier function- induced neural controller. In 2024 IEEE International Conference on Robotics and Automation (ICRA) , pages 14348–14355, 2024. 2, 3

work page 2024

[47] [47]

Efficient collision detection framework for enhancing collision-free robot motion

Xiankun Zhu, Yucheng Xin, Shoujie Li, Houde Liu, Chongkun Xia, and Bin Liang. Efficient collision detection framework for enhancing collision-free robot motion. arXiv preprint arXiv:2409.14955, 2024. 1, 2, 8, 9, 10

work page arXiv 2024