pith. machine review for the scientific record. sign in

arxiv: 2604.06133 · v1 · submitted 2026-04-07 · 💻 cs.RO

Recognition: 2 theorem links

· Lean Theorem

Learning-Guided Force-Feedback Model Predictive Control with Obstacle Avoidance for Robotic Deburring

Krzysztof Wojciechowski , Ege Gursoy , Arthur Haffemayer , Sebastien Kleff , Vincent Bonnet , Florent Lamiraux , Nicolas Mansard
Authors on Pith no claims yet

Pith reviewed 2026-05-10 18:47 UTC · model grok-4.3

classification 💻 cs.RO
keywords robotic deburringforce-feedback MPCdiffusion motion priorsobstacle avoidancecontact-rich taskstorque-controlled robotsmodel predictive controlindustrial manipulation
0
0 comments X

The pith

Integrating diffusion-based motion priors with force-feedback MPC enables reliable tool insertion, accurate force tracking, and collision-free circular deburring in hard-to-reach robot configurations.

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

The paper establishes that classical MPC struggles with contact-rich deburring because it lacks good motion strategies for tool insertion and circular paths under force and collision limits. By treating a diffusion model as a learned memory of successful motions, the approach supplies initial trajectories that the MPC then refines while enforcing explicit normal-force regulation, torque bounds, and obstacle avoidance. Experiments on a torque-controlled arm confirm that this hybrid controller succeeds where standard pipelines do not, even in awkward poses with nearby obstacles. A reader would care because deburring and similar industrial contact tasks currently require heavy manual tuning or conservative safety margins that slow production.

Core claim

The proposed framework integrates force-feedback MPC with diffusion-based motion priors. The diffusion model acts as a memory of motion strategies that supplies robust initialization and adaptation across task instances. MPC then guarantees safe execution through explicit force tracking, torque feasibility, and collision avoidance. Validation on a torque-controlled manipulator shows reliable tool insertion, accurate normal force tracking, and circular deburring motions in hard-to-reach configurations under obstacle constraints, constituting the first reported integration of these components for collision-aware, contact-rich industrial tasks.

What carries the argument

Diffusion model serving as a motion prior that supplies initialization and adaptation, coupled to force-feedback MPC that enforces real-time force, torque, and collision constraints.

If this is right

  • The robot can insert the tool and regulate contact force accurately even in configurations that defeat standard MPC.
  • Circular deburring paths remain collision-free while satisfying torque limits.
  • The same learned prior supports adaptation to new but similar task instances without retuning the controller.
  • Force-feedback and collision avoidance operate simultaneously in real time on torque-controlled hardware.

Where Pith is reading between the lines

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

  • The same pattern of learned motion memory plus constraint-based optimization could transfer to other contact-rich tasks such as polishing or assembly.
  • Reducing reliance on manual trajectory design may shorten deployment time for new deburring or grinding cells.
  • If the diffusion prior can be updated online from successful executions, the system might improve over repeated production runs.

Load-bearing premise

The diffusion model supplies initializations and adaptations that stay compatible with the MPC constraints on force, torque, and collisions.

What would settle it

An experiment in which the combined system repeatedly fails to maintain accurate normal force tracking or complete circular motions when obstacles are present would disprove the claim that the integration delivers reliable performance.

Figures

Figures reproduced from arXiv: 2604.06133 by Arthur Haffemayer, Ege Gursoy, Florent Lamiraux, Krzysztof Wojciechowski, Nicolas Mansard, Sebastien Kleff, Vincent Bonnet.

Figure 1
Figure 1. Figure 1: Torque-controlled Franka Emika Panda robot exe [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: To this end, we define it as the insertion of a precision [PITH_FULL_IMAGE:figures/full_fig_p002_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Custom end-effector mount for the Franka Emika [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Representative sequence of a circular deburring [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Scenario 1 (Sec. V-C): Force-colored end-effector x-y [PITH_FULL_IMAGE:figures/full_fig_p005_5.png] view at source ↗
Figure 7
Figure 7. Figure 7: Positions of the 5 holes to be deburred on the investigated workpiece and reaching postures for each hole. [PITH_FULL_IMAGE:figures/full_fig_p006_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Description of the collision pair between the plane [PITH_FULL_IMAGE:figures/full_fig_p006_8.png] view at source ↗
read the original abstract

Model Predictive Control (MPC) is widely used for torque-controlled robots, but classical formulations often neglect real-time force feedback and struggle with contact-rich industrial tasks under collision constraints. Deburring in particular requires precise tool insertion, stable force regulation, and collision-free circular motions in challenging configurations, which exceeds the capability of standard MPC pipelines. We propose a framework that integrates force-feedback MPC with diffusion-based motion priors to address these challenges. The diffusion model serves as a memory of motion strategies, providing robust initialization and adaptation across multiple task instances, while MPC ensures safe execution with explicit force tracking, torque feasibility, and collision avoidance. We validate our approach on a torque-controlled manipulator performing industrial deburring tasks. Experiments demonstrate reliable tool insertion, accurate normal force tracking, and circular deburring motions even in hard-to-reach configurations and under obstacle constraints. To our knowledge, this is the first integration of diffusion motion priors with force-feedback MPC for collision-aware, contact-rich industrial tasks.

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.

Referee Report

0 major / 3 minor

Summary. The manuscript proposes integrating diffusion-based motion priors with force-feedback Model Predictive Control (MPC) for robotic deburring on torque-controlled manipulators. The diffusion model acts as a learned memory of motion strategies to provide robust initialization and adaptation, while MPC enforces explicit constraints on normal force tracking, torque feasibility, and collision avoidance. Experiments claim to demonstrate reliable tool insertion, accurate force regulation, and circular deburring motions in hard-to-reach configurations under obstacle constraints, positioning the work as the first such integration for contact-rich industrial tasks.

Significance. If the experimental validation holds with supporting quantitative metrics, the result is significant for advancing hybrid learning-optimization approaches in robotics. It addresses a practical gap where classical MPC struggles with contact-rich tasks by using diffusion priors for feasible trajectory initialization while retaining safety guarantees through optimization. This could enable more reliable deployment in industrial settings requiring precise force control and obstacle handling.

minor comments (3)
  1. Abstract: The summary of experimental outcomes would be strengthened by including at least one quantitative metric (e.g., force tracking RMSE or success rate) rather than qualitative descriptors alone.
  2. The manuscript should clarify how the diffusion prior is exactly interfaced with the MPC (e.g., as warm-start trajectories or as a cost term) to make the integration reproducible.
  3. Ensure all experimental figures include axis labels, units, and direct comparison to baseline methods where applicable.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive assessment of our manuscript, recognition of its significance for hybrid learning-optimization approaches in contact-rich robotics, and recommendation for minor revision. We are pleased that the integration of diffusion-based motion priors with force-feedback MPC is viewed as addressing a practical gap in industrial deburring tasks.

Circularity Check

0 steps flagged

No significant circularity; integration of independent components

full rationale

The manuscript describes an engineering integration of diffusion-based motion priors (for initialization and adaptation) with force-feedback MPC (for constraint enforcement on force, torque, and collisions). No equations, derivations, or parameter-fitting steps are presented that reduce the central claims to self-definition or fitted inputs by construction. The diffusion model is treated as an external learned component providing feasible trajectories, while MPC handles explicit optimization; these are distinct modules with no load-bearing self-citation chain or ansatz smuggling. Experimental validation on insertion, force tracking, and obstacle avoidance stands as independent evidence rather than a renamed or forced result. This is the expected non-finding for an applied robotics paper without a closed mathematical derivation.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review provides no explicit free parameters, axioms, or invented entities; the diffusion model is treated as a black-box learned component whose training details are not described.

pith-pipeline@v0.9.0 · 5492 in / 1115 out tokens · 42672 ms · 2026-05-10T18:47:39.461749+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

52 extracted references · 10 canonical work pages · 1 internal anchor

  1. [1]

    Feedback MPC for Torque-Controlled Legged Robots,

    R. Grandia, F. Farshidian, R. Ranftl, and M. Hutter, “Feedback MPC for Torque-Controlled Legged Robots,” Aug. 2019, arXiv:1905.06144 [cs]. [Online]. Available: http://arxiv.org/abs/1905.06144

    work page arXiv 2019

  2. [2]

    Online Non-linear Centroidal MPC for Humanoid Robot Locomotion with Step Adjustment,

    G. Romualdi, S. Dafarra, G. L’Erario, I. Sorrentino, S. Traversaro, and D. Pucci, “Online Non-linear Centroidal MPC for Humanoid Robot Locomotion with Step Adjustment,” in2022 International Conference on Robotics and Automation (ICRA), 2022, pp. 10 412–10 419

    2022

  3. [3]

    Whole-Body Model Predictive Control for Biped Locomotion on a Torque-Controlled Humanoid Robot,

    E. Dantec, M. Naveau, P. Fernbach, N. Villa, G. Saurel, O. Stasse, M. Taix, and N. Mansard, “Whole-Body Model Predictive Control for Biped Locomotion on a Torque-Controlled Humanoid Robot,” in 2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids), 2022, pp. 638–644

    2022

  4. [4]

    Collision- Free MPC for Legged Robots in Static and Dynamic Scenes,

    M. Gaertner, M. Bjelonic, F. Farshidian, and M. Hutter, “Collision- Free MPC for Legged Robots in Static and Dynamic Scenes,” in2021 IEEE International Conference on Robotics and Automation (ICRA), May 2021, pp. 8266–8272, iSSN: 2577-087X. [Online]. Available: https://ieeexplore.ieee.org/document/9561326

    work page arXiv 2021

  5. [5]

    Collision Avoidance in Model Predictive Control using Velocity Damper,

    A. Haffemayer, A. Jordana, L. de Matte ¨ıs, K. Wojciechowski, L. Righetti, F. Lamiraux, and N. Mansard, “Collision Avoidance in Model Predictive Control using Velocity Damper,” in2025 IEEE International Conference on Robotics and Automation (ICRA), May

  6. [6]

    Available: https://laas.hal.science/hal-04707324

    [Online]. Available: https://laas.hal.science/hal-04707324

  7. [7]

    Real-time motion planning of legged robots: A model predictive con- trol approach,

    F. Farshidian, E. Jelavic, A. Satapathy, M. Giftthaler, and J. Buchli, “Real-time motion planning of legged robots: A model predictive con- trol approach,” inIEEE-RAS International Conference on Humanoid Robotics (Humanoids), 2017

    2017

  8. [8]

    Percep- tive Locomotion Through Nonlinear Model-Predictive Control,

    R. Grandia, F. Jenelten, S. Yang, F. Farshidian, and M. Hutter, “Percep- tive Locomotion Through Nonlinear Model-Predictive Control,”IEEE Transactions on Robotics, vol. 39, no. 5, pp. 3402–3421, 2023

    2023

  9. [9]

    Inverse-Dynamics MPC via Nullspace Resolution,

    C. Mastalli, S. P. Chhatoi, T. Corberes, S. Tonneau, and S. Vi- jayakumar, “Inverse-Dynamics MPC via Nullspace Resolution,”IEEE Transactions on Robotics, vol. 39, no. 4, pp. 3222–3241, 2023

    2023

  10. [10]

    Force feedback control of manipulator fine motions,

    D. E. Whitney, “Force feedback control of manipulator fine motions,” Journal of Dynamic Systems Measurement and Control-transactions of The Asme, vol. 99, pp. 91–97, 1977. [Online]. Available: https://api.semanticscholar.org/CorpusID:121383894

    1977

  11. [11]

    Villani and J

    L. Villani and J. De Schutter,Force Control. Berlin, Heidelberg: Springer Berlin Heidelberg, 2008, pp. 161–185. [Online]. Available: https://doi.org/10.1007/978-3-540-30301-5 8

    work page doi:10.1007/978-3-540-30301-5 2008

  12. [12]

    Compliance and Force Control for Computer Con- trolled Manipulators,

    M. T. Mason, “Compliance and Force Control for Computer Con- trolled Manipulators,”IEEE Transactions on Systems, Man and Cy- bernetics, vol. 11, no. 6, pp. 418–432, 1981

    1981

  13. [13]

    Impedance Control Part1-3,

    N. Hogan, “Impedance Control Part1-3,”J. Dyn. Sys., Meas., Control., vol. 107, pp. 1–24, 1985

    1985

  14. [14]

    Model predictive control for fast reaching in clutter,

    M. D. Killpack, A. Kapusta, and C. C. Kemp, “Model predictive control for fast reaching in clutter,”Autonomous Robots, vol. 40, no. 3, pp. 537–560, 2016

    2016

  15. [15]

    Force Feedback and Path Following using Predictive Control: Concept and Application to a Lightweight Robot,

    J. Matschek, J. Bethge, P. Zometa, and R. Findeisen, “Force Feedback and Path Following using Predictive Control: Concept and Application to a Lightweight Robot,”IFAC-PapersOnLine, vol. 50, 2017

    2017

  16. [16]

    Model Predictive Force Control in Grinding based on a Lightweight Robot,

    S. Husmann, S. Stemmler, S. H ¨ahnel, S. V ogelgesang, D. Abel, and T. Bergs, “Model Predictive Force Control in Grinding based on a Lightweight Robot,”IFAC-PapersOnLine, vol. 52, 2019

    2019

  17. [17]

    Model predictive force control for robots in compliant environments with guaranteed maximum force,

    D. M ¨uller, A. Mayer, and O. Sawodny, “Model predictive force control for robots in compliant environments with guaranteed maximum force,” in2019 American Control Conference (ACC), 2019, pp. 1355– 1360

    2019

  18. [18]

    MPC-based admittance control for robotic manipulators,

    A. Wahrburg and K. Listmann, “MPC-based admittance control for robotic manipulators,”2016 IEEE 55th Conference on Decision and Control, CDC 2016, pp. 7548–7554, dec 2016

    2016

  19. [19]

    Perceptive model predictive control for continuous mobile manipulation,

    J. Pankert and M. Hutter, “Perceptive model predictive control for continuous mobile manipulation,”IEEE Robotics and Automation Letters, vol. 5, no. 4, pp. 6177–6184, oct 2020

    2020

  20. [20]

    Combined Predictive Path Following and Admittance Control,

    K. J. Kazim, J. Bethge, J. Matschek, and R. Findeisen, “Combined Predictive Path Following and Admittance Control,”Proceedings of the American Control Conference, vol. 2018-June, pp. 3153–3158, aug 2018

    2018

  21. [21]

    Model Predictive Robot-Environment Interaction Control for Mobile Manipulation Tasks,

    M. V . Minniti, R. Grandia, K. F ¨ah, F. Farshidian, and M. Hutter, “Model Predictive Robot-Environment Interaction Control for Mobile Manipulation Tasks,”Proceedings - IEEE International Conference on Robotics and Automation, vol. 2021-May, no. Icra, pp. 1651–1657, 2021

    2021

  22. [22]

    Whole-Body Nonlinear Model Predictive Control Through Contacts for Quadrupeds,

    M. Neunert, M. Stauble, M. Giftthaler, C. D. Bellicoso, J. Carius, C. Gehring, M. Hutter, and J. Buchli, “Whole-Body Nonlinear Model Predictive Control Through Contacts for Quadrupeds,”IEEE Robotics and Automation Letters, vol. 3, no. 3, pp. 1458–1465, 2018

    2018

  23. [23]

    STANCE: Locomotion Adaptation over Soft Terrain,

    S. Fahmi, M. Focchi, A. Radulescu, G. Fink, V . Barasuol, and C. Semini, “STANCE: Locomotion Adaptation over Soft Terrain,” IEEE TRO, vol. 36, no. 2, apr 2020

    2020

  24. [24]

    Model Predictive Interaction Control for Robotic Manipulation Tasks,

    T. Gold, A. V ¨olz, and K. Graichen, “Model Predictive Interaction Control for Robotic Manipulation Tasks,”IEEE Transactions on Robotics, vol. 39, no. 1, pp. 76–89, 2023

    2023

  25. [25]

    Intro- ducing force feedback in model predictive control,

    S. Kleff, E. Dantec, G. Saurel, N. Mansard, and L. Righetti, “Intro- ducing force feedback in model predictive control,” in2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022, pp. 13 379–13 385

    2022

  26. [26]

    Jerk control of floating base systems with contact-stable parameterized force feed- back,

    A. Gazar, G. Nava, F. J. A. Chavez, and D. Pucci, “Jerk control of floating base systems with contact-stable parameterized force feed- back,”IEEE Transactions on Robotics, vol. 37, no. 1, pp. 1–15, 2021

    2021

  27. [27]

    Real- Time Deformable-Contact-Aware Model Predictive Control for Force- Modulated Manipulation,

    L. Wijayarathne, Z. Zhou, Y . Zhao, and F. L. Hammond, “Real- Time Deformable-Contact-Aware Model Predictive Control for Force- Modulated Manipulation,”IEEE Transactions on Robotics, vol. 39, no. 5, pp. 3549–3566, 2023

    2023

  28. [28]

    Non-prehensile object transportation via model predictive non-sliding manipulation control,

    M. Selvaggio, A. Garg, F. Ruggiero, G. Oriolo, and B. Siciliano, “Non-prehensile object transportation via model predictive non-sliding manipulation control,”IEEE Transactions on Control Systems Tech- nology, vol. 31, no. 5, pp. 2231–2244, 2023

    2023

  29. [29]

    Force Feedback in Model Predictive Control: A Soft Contact Approach,

    S. Kleff, A. Jordana, N. Mansard, and L. Righetti, “Force Feedback in Model Predictive Control: A Soft Contact Approach,” May 2024, working paper or preprint. [Online]. Available: https: //hal.science/hal-04572399

    2024

  30. [30]

    Industrial Robots in Mechanical Machining: Perspectives and Limitations,

    M. Makulavi ˇcius, S. Petkevi ˇcius, J. Ro ˇz˙en˙e, A. Dzedzickis, and V . Bu ˇcinskas, “Industrial Robots in Mechanical Machining: Perspectives and Limitations,”Robotics, vol. 12, no. 6, 2023. [Online]. Available: https://www.mdpi.com/2218-6581/12/6/160

    2023

  31. [31]

    Trajectory prediction: learning to map situations to robot trajectories,

    N. Jetchev and M. Toussaint, “Trajectory prediction: learning to map situations to robot trajectories,” inProceedings of the 26th Annual International Conference on Machine Learning, ser. ICML ’09. New York, NY , USA: Association for Computing Machinery, 2009, pp. 449–456, event-place: Montreal, Quebec, Canada. [Online]. Available: https://doi.org/10.1145...

    work page doi:10.1145/1553374.1553433 2009

  32. [32]

    Using a Memory of Motion to Efficiently Warm-Start a Nonlinear Predictive Controller,

    N. Mansard, A. DelPrete, M. Geisert, S. Tonneau, and O. Stasse, “Using a Memory of Motion to Efficiently Warm-Start a Nonlinear Predictive Controller,” in2018 IEEE International Conference on Robotics and Automation (ICRA), May 2018, pp. 2986–2993, iSSN: 2577-087X. [Online]. Available: https://ieeexplore.ieee.org/document/ 8463154

    2018

  33. [33]

    Learning How to Walk: Warm-starting Optimal Control Solver with Memory of Motion,

    T. S. Lembono, C. Mastalli, P. Fernbach, N. Mansard, and S. Calinon, “Learning How to Walk: Warm-starting Optimal Control Solver with Memory of Motion,” in2020 IEEE International Conference on Robotics and Automation (ICRA), May 2020, pp. 1357–1363, iSSN: 2577-087X. [Online]. Available: https: //ieeexplore.ieee.org/document/9196727

    work page arXiv 2020

  34. [34]

    Whole Body Model Predictive Control with a Memory of Motion: Experiments on a Torque-Controlled Talos,

    E. Dantec, R. Budhiraja, A. Roig, T. Lembono, G. Saurel, O. Stasse, P. Fernbach, S. Tonneau, S. Vijayakumar, S. Calinon, M. Taix, and N. Mansard, “Whole Body Model Predictive Control with a Memory of Motion: Experiments on a Torque-Controlled Talos,” in2021 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2021, pp. 8975–8981

    2021

  35. [35]

    Planning with Diffusion for Flexible Behavior Synthesis,

    M. Janner, Y . Du, J. B. Tenenbaum, and S. Levine, “Planning with Diffusion for Flexible Behavior Synthesis,” inInternational Conference on Machine Learning, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:248965046

    2022

  36. [36]

    V ., Guntupalli, J

    G. Zhou, S. Swaminathan, R. V . Raju, J. S. Guntupalli, W. Lehrach, J. Ortiz, A. Dedieu, M. L ´azaro-Gredilla, and K. Murphy, “Diffusion Model Predictive Control,” Oct. 2024, arXiv:2410.05364 [cs]. [Online]. Available: http://arxiv.org/abs/2410.05364

    work page arXiv 2024

  37. [37]

    Diffusion policy: Visuomotor policy learning via action diffusion,

    C. Chi, Z. Xu, S. Feng, E. Cousineau, Y . Du, B. Burchfiel, R. Tedrake, and S. Song, “Diffusion policy: Visuomotor policy learning via action diffusion,”The International Journal of Robotics Research, p. 02783649241273668, Oct. 2024, publisher: SAGE Publications Ltd STM. [Online]. Available: https://doi.org/10.1177/ 02783649241273668

    2024

  38. [38]

    Differential dynamic programming for multi-phase rigid contact dynamics,

    R. Budhiraja, J. Carpentier, C. Mastalli, and N. Mansard, “Differential dynamic programming for multi-phase rigid contact dynamics,” in IEEE Humanoids, 2018

    2018

  39. [39]

    Structure-Exploiting Sequential Quadratic Programming for Model-Predictive Control,

    A. Jordana, S. Kleff, A. Meduri, J. Carpentier, N. Mansard, and L. Righetti, “Structure-Exploiting Sequential Quadratic Programming for Model-Predictive Control,”IEEE Transactions on Robotics, Aug

  40. [40]

    Available: https://laas.hal.science/hal-04330251

    [Online]. Available: https://laas.hal.science/hal-04330251

  41. [41]

    Model predictive control under hard collision avoidance constraints for a robotic arm,

    A. Haffemayer, A. Jordana, M. Fourmy, K. Wojciechowski, G. Saurel, V . Petr´ık, F. Lamiraux, and N. Mansard, “Model predictive control under hard collision avoidance constraints for a robotic arm,” inUbiquitous Robots 2024. New York (USA), United States: Korea Robotics Society, June 2024. [Online]. Available: https://laas.hal.science/hal-04425002

    2024

  42. [42]

    Hpp: A new software for constrained motion planning,

    J. Mirabel, S. Tonneau, P. Fernbach, A.-K. Sepp”al”a, M. Campana, N. Mansard, and F. Lamiraux, “Hpp: A new software for constrained motion planning,” in2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2016, pp. 383–389

    2016

  43. [43]

    Scalable Diffusion Models with Transformers

    W. Peebles and S. Xie, “Scalable Diffusion Models with Transformers,” Mar. 2023, arXiv:2212.09748 [cs]. [Online]. Available: http://arxiv.org/abs/2212.09748

    work page internal anchor Pith review arXiv 2023

  44. [44]

    Denoising diffusion probabilistic models,

    J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” inProceedings of the 34th International Conference on Neural Information Processing Systems, ser. NIPS ’20. Red Hook, NY , USA: Curran Associates Inc., 2020, event-place: Vancouver, BC, Canada

    2020

  45. [45]

    Collision-free model predictive control with diffusion model warm-starting,

    A. Haffemayer, A. Chapin, K. Wojciechowski, A. Jordana, F. Lami- raux, V . Petr ´ık, and N. Mansard, “Collision-free model predictive control with diffusion model warm-starting,” 2025, preprint, submitted to RAL

    2025

  46. [46]

    Crocoddyl: An efficient and versatile framework for multi-contact optimal control,

    C. Mastalli, R. Budhiraja, W. Merkt, G. Saurel, B. Hammoud, M. Naveau, J. Carpentier, S. Vijayakumar, and N. Mansard, “Crocoddyl: An efficient and versatile framework for multi-contact optimal control,”CoRR, vol. abs/1909.04947, 2019. [Online]. Available: http://arxiv.org/abs/1909.04947

    work page arXiv 1909

  47. [47]

    Manipulability of robotic mechanisms,

    T. Yoshikawa, “Manipulability of robotic mechanisms,”The interna- tional journal of Robotics Research, vol. 4, no. 2, pp. 3–9, 1985

    1985

  48. [48]

    Massively parallelizing the rrt and the rrt,

    J. Bialkowski, S. Karaman, and E. Frazzoli, “Massively parallelizing the rrt and the rrt,” in2011 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, 2011, pp. 3513–3518

    2011

  49. [49]

    pRRTC: GPU-Parallel RRT-Connect for Fast, Consistent, and Low-Cost Mo- tion Planning

    C. H. Huang, P. Jadhav, B. Plancher, and Z. Kingston, “prrtc: Gpu- parallel rrt-connect for fast, consistent, and low-cost motion planning,” arXiv preprint arXiv:2503.06757, 2025

    work page arXiv 2025

  50. [50]

    Hpipm: a high-performance quadratic programming framework for model predictive control,

    G. Frison and M. Diehl, “Hpipm: a high-performance quadratic programming framework for model predictive control,”arXiv preprint arXiv:2003.02547, 2020. [Online]. Available: https://arxiv.org/abs/ 2003.02547

    work page arXiv 2003

  51. [51]

    Fast manipulability maximization using continuous-time trajectory optimization,

    F. Mari’c, O. Limoyo, L. Petrovi’c, T. Ablett, I. Petrovi’c, and J. Kelly, “Fast manipulability maximization using continuous-time trajectory optimization,” in2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2019, pp. 8258– 8264

    2019

  52. [52]

    Manipulability op- timization for multi-arm teleoperation,

    F. Kennel-Maushart, R. Poranne, and S. Coros, “Manipulability op- timization for multi-arm teleoperation,” in2021 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2021, pp. 3956–3962

    2021