pith. machine review for the scientific record.
sign in

arxiv: 2509.21020 · v2 · submitted 2025-09-25 · 💻 cs.RO

Hybrid Task and Motion Planning with Reactive Collision Handling for Multi-Robot Disassembly of Complex Products: Application to EV Batteries

Abdelaziz Shaarawy , Cansu Erdogan , Rustam Stolkin , Alireza Rastegarpanah This is my paper

Pith reviewed 2026-05-18 14:13 UTC · model grok-4.3

classification 💻 cs.RO
keywords multi-robot coordinationtask and motion planningEV battery disassemblycollision avoidancevision-driven planningreactive replanninghybrid safety layer
0
0 comments X

The pith

A closed-loop vision-driven task and motion planner for two robots cuts total path length by 63 percent during EV battery disassembly.

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

The paper presents a framework that decomposes disassembly tasks, allocates them to two robots, and plans motions using a learning-based RRT planner informed by Gaussian mixture models. It adds a hybrid safety layer that checks for collisions in a digital twin while also using live vision to reactively avoid obstacles and replan. The system runs in closed loop, rescanning the scene to update what tasks remain instead of following a fixed plan. In real experiments on EV batteries this approach produced much shorter paths, slightly faster overall time, and smaller volumes of space swept by the arms compared with a standard motion planner under the same task assignments. A sympathetic reader would care because safer and more efficient multi-robot disassembly could make recycling complex products like batteries more practical and less risky.

Core claim

The proposed vision-driven TAMP framework integrates task decomposition and allocation with a GMM-informed RRT motion planner and a hybrid safety layer of predictive collision checking in a MoveIt/FCL digital twin together with reactive vision-based avoidance and replanning. Operating in closed loop by updating the remaining task sequence from repeated scene scans and completion-state tracking, the system satisfies task precedence, geometric feasibility, dynamic obstacle avoidance, and dual-arm coordination constraints simultaneously.

What carries the argument

The hybrid safety layer that combines predictive collision checking in a digital twin with reactive vision-based avoidance and replanning, coupled with closed-loop task sequence updates from vision.

If this is right

  • Reduces cumulative end-effector path length from 48.8 m to 17.9 m in EV battery disassembly experiments.
  • Improves makespan from 467.9 s to 429.8 s under identical perception and task assignments.
  • Reduces swept volumes for each robot and their overlap volume.
  • Improves motion compactness, safety, and scalability to broader multi-robot sequential manipulation tasks.

Where Pith is reading between the lines

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

  • The approach could extend to other complex product disassembly where perception can track progress reliably.
  • Combining predictive and reactive methods may generalize to other dual-arm coordination problems beyond disassembly.
  • Further scaling might require handling more than two robots or additional uncertainty sources.
  • Testable by applying the same framework to different battery types or product categories.

Load-bearing premise

The framework assumes vision can reliably and timely track task completions and update the remaining sequence without significant errors, delays, or occlusions that invalidate task or geometric constraints.

What would settle it

A set of experiments introducing realistic perception errors, delays, or occlusions during disassembly that cause the system to fail task precedence or produce paths no better than the default RRTConnect planner.

Figures

Figures reproduced from arXiv: 2509.21020 by Abdelaziz Shaarawy, Alireza Rastegarpanah, Cansu Erdogan, Rustam Stolkin.

Figure 1
Figure 1. Figure 1: The overall architecture of the collision detection and motion planning [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview of the proposed Task and Motion Planning (TAMP) framework in dual-arm setups. The framework integrates multi-level vision-driven object [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 4
Figure 4. Figure 4: Illustration of the developed avoid_collision() routine, which is invoked when two robots approach near-collision while executing planned trajectories. The red spheres represent collision objects (in this case, robot 1’s link4 and camera2), which FCL identifies as ’in collision’ when the distance between them falls below the threshold ε. This adaptive behaviour avoids unnecessary trajectory de￾viations, he… view at source ↗
Figure 5
Figure 5. Figure 5: Case study I: Robot-to-robot interaction. Comparison between (a) [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 7
Figure 7. Figure 7: The workspace with a battery pack disassembly setup, equipped with [PITH_FULL_IMAGE:figures/full_fig_p008_7.png] view at source ↗
Figure 6
Figure 6. Figure 6: Case Study II: Robot-to-dynamic environment interaction. Comparison [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 8
Figure 8. Figure 8: Comparison of Path Deviations due to collisions detected whilst [PITH_FULL_IMAGE:figures/full_fig_p009_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Comparison of TP-GMM Planner and Default Planner in terms of (a) [PITH_FULL_IMAGE:figures/full_fig_p010_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Comparison of manipulability Index for two trajectory solutions [PITH_FULL_IMAGE:figures/full_fig_p010_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Swept volume per robot via isosurface rendering. (a) Default vs (b) [PITH_FULL_IMAGE:figures/full_fig_p011_11.png] view at source ↗
read the original abstract

This paper addresses the problem of multi-robot coordination for complex manipulation task sequences. We present a vision-driven task-and-motion planning (TAMP) framework for a real dual-agent platform that integrates task decomposition and allocation with a learning-based RRT planner. A GMM-informed motion planner is coupled with a hybrid safety layer that combines predictive collision checking in a MoveIt/FCL digital twin with reactive vision-based avoidance and replanning. This integration is challenging as the system jointly satisfies task precedence, geometric feasibility, dynamic obstacle avoidance, and dual-arm coordination constraints. The framework operates in closed loop by updating the remaining task sequence from repeated scene scans and completion-state tracking rather than executing a fixed open-loop plan. In EV battery disassembly experiments, compared with Default-RRTConnect under identical perception and task assignments, the proposed system reduces cumulative end-effector path length from 48.8 to 17.9~m ($-63.3\%$), improves makespan from 467.9 to 429.8~s ($-8.1\%$), and reduces swept volumes (R1: $0.583\rightarrow0.139\,\mathrm{m}^3$, R2: $0.696\rightarrow0.252\,\mathrm{m}^3$) and overlap ($0.064\rightarrow0.034\,\mathrm{m}^3$). These results show that combining predictive planning and reactive collision avoidance in a real dual-arm disassembly scenario improves motion compactness, safety, and scalability to broader multi-robot sequential manipulation 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

1 major / 2 minor

Summary. The paper presents a vision-driven hybrid task-and-motion planning (TAMP) framework for multi-robot disassembly of complex products, demonstrated on EV batteries with a real dual-arm platform. It integrates task decomposition/allocation, a GMM-informed learning-based RRT motion planner, and a hybrid safety layer that combines predictive collision checking in a MoveIt/FCL digital twin with reactive vision-based avoidance and replanning. The system runs in closed loop by repeatedly scanning the scene to update the remaining task sequence and completion state, rather than using a fixed open-loop plan. Experiments report concrete gains versus Default-RRTConnect under identical perception and task assignments: cumulative end-effector path length reduced from 48.8 m to 17.9 m (−63.3 %), makespan from 467.9 s to 429.8 s (−8.1 %), and lower swept volumes (R1: 0.583→0.139 m³, R2: 0.696→0.252 m³) plus overlap (0.064→0.034 m³).

Significance. If the central claims hold, the work shows that coupling predictive planning with reactive vision-based collision handling can deliver substantial improvements in motion compactness, safety, and coordination for sequential multi-robot manipulation on physical hardware. The manuscript earns credit for reporting concrete quantitative improvements on a real dual-arm platform with a named baseline (Default-RRTConnect) under matched perception and task conditions, together with direct physical measurements of path length, makespan, and swept volumes. These elements strengthen its relevance for practical robotic disassembly and recycling applications.

major comments (1)
  1. [EV Battery Disassembly Experiments] EV Battery Disassembly Experiments: the reported performance gains (−63.3 % path length, −8.1 % makespan, reduced swept volumes) are obtained under closed-loop operation that repeatedly updates the task sequence from vision-based scene scans and completion-state tracking. The manuscript provides no quantitative data on perception reliability (e.g., false-negative rates for part removal, occlusion handling, or latency), which is load-bearing for preserving task precedence and geometric feasibility; a single missed detection could invalidate subsequent plans and erase the claimed benefits.
minor comments (2)
  1. [Abstract] Abstract and results presentation: the abstract and experimental section should state the number of trials performed and report statistical variability (standard deviations or confidence intervals) for all metrics; without these the reproducibility of the −63.3 % and −8.1 % figures cannot be fully assessed.
  2. [Framework Description] Notation and implementation clarity: the exact interface between the predictive FCL checker and the reactive vision avoidance (e.g., priority rules, replanning trigger thresholds) is described only at a high level; a diagram or pseudocode would improve reproducibility.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback and for recognizing the quantitative gains demonstrated on the physical dual-arm platform. We respond to the major comment below.

read point-by-point responses

  1. Referee: [EV Battery Disassembly Experiments] EV Battery Disassembly Experiments: the reported performance gains (−63.3 % path length, −8.1 % makespan, reduced swept volumes) are obtained under closed-loop operation that repeatedly updates the task sequence from vision-based scene scans and completion-state tracking. The manuscript provides no quantitative data on perception reliability (e.g., false-negative rates for part removal, occlusion handling, or latency), which is load-bearing for preserving task precedence and geometric feasibility; a single missed detection could invalidate subsequent plans and erase the claimed benefits.

    Authors: We agree that the manuscript does not include quantitative metrics on perception reliability such as false-negative rates, occlusion statistics, or measured latency. The reported performance improvements were obtained from successful physical executions of the complete disassembly sequence under the closed-loop vision-driven system. In these trials the perception pipeline correctly identified all part removals and maintained valid task precedence without errors that invalidated subsequent plans. In the revised version we will add a short subsection in the experimental evaluation that describes the observed perception behavior during the reported runs, including how occlusions were managed by the repeated scanning cycle and the approximate update latency of the closed loop. This addition will provide readers with the necessary context for interpreting the robustness of the claimed gains. revision: partial

Circularity Check

0 steps flagged

No significant circularity in experimental framework or results

full rationale

The paper presents a hybrid TAMP framework for multi-robot EV battery disassembly, validated through direct physical experiments comparing the proposed system to Default-RRTConnect under identical perception and task assignments. Reported improvements (path length, makespan, swept volumes) are measured outcomes on real hardware rather than derived predictions. No equations, self-definitional reductions, fitted parameters renamed as predictions, or load-bearing self-citations appear in the provided text; the closed-loop vision updates are an operational assumption, not a circular derivation step. The derivation chain is self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claims rest on standard robotics domain assumptions about perception reliability and planner integration rather than new free parameters or invented entities.

axioms (1)
  • domain assumption Vision system provides sufficiently accurate and timely updates to scene state and task completion for closed-loop replanning
    Invoked to justify updating the remaining task sequence from repeated scene scans rather than executing a fixed open-loop plan.

pith-pipeline@v0.9.0 · 5823 in / 1345 out tokens · 45537 ms · 2026-05-18T14:13:25.699468+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

37 extracted references · 37 canonical work pages · 1 internal anchor

  1. [1]

    Robust and efficient task scheduling for robotics applications with reinforcement learning,

    M. Tejer, R. Szczepanski, and T. Tarczewski, “Robust and efficient task scheduling for robotics applications with reinforcement learning,” Engineering Applications of Artificial Intelligence, vol. 127, p. 107300, 2024

    work page 2024

  2. [2]

    Scheduling of multi-robot job shop systems in dy- namic environments: Mixed-integer linear programming and constraint programming approaches,

    S. Fatemi-Anaraki, R. Tavakkoli-Moghaddam, M. Foumani, and B. Vahedi-Nouri, “Scheduling of multi-robot job shop systems in dy- namic environments: Mixed-integer linear programming and constraint programming approaches,”Omega, vol. 115, p. 102770, 2023

    work page 2023

  3. [3]

    Efficient industrial solution for robotic task sequencing problem with mutual collision avoidance & cycle time optimization,

    H. Touzani, N. S ´eguy, H. Hadj-Abdelkader, R. Su ´arez, J. Rosell, L. Palomo-Avellaneda, and S. Bouchafa, “Efficient industrial solution for robotic task sequencing problem with mutual collision avoidance & cycle time optimization,”IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 2597–2604, 2022

    work page 2022

  4. [4]

    Disassembly of electric vehicle batteries using the example of the audi q5 hybrid system,

    K. Wegener, S. Andrew, A. Raatz, K. Dr ¨oder, and C. Herrmann, “Disassembly of electric vehicle batteries using the example of the audi q5 hybrid system,”Procedia CIRP, vol. 23, pp. 155–160, 2014, 5th CATS 2014 - CIRP Conference on Assembly Technologies and Systems

    work page 2014

  5. [5]

    Abatre-sim: A comprehensive framework for automated battery recycling simulation,

    H. Wang, K. Zhang, K. Zhu, Z. Song, and Z. Li, “Abatre-sim: A comprehensive framework for automated battery recycling simulation,” 2023 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1–8, 2023

    work page 2023

  6. [6]

    Reducing the Barrier to Entry of Complex Robotic Software: a MoveIt! Case Study

    D. Coleman, I. A. Sucan, S. Chitta, and N. Correll, “Reducing the barrier to entry of complex robotic software: a moveit! case study,”CoRR, vol. abs/1404.3785, 2014

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  7. [7]

    Fcl: A general purpose library for collision and proximity queries,

    J. Pan, S. Chitta, and D. Manocha, “Fcl: A general purpose library for collision and proximity queries,” in2012 IEEE International Conference on Robotics and Automation, 2012, pp. 3859–3866

    work page 2012

  8. [8]

    Optimal robot task schedul- ing based on adaptive neuro-fuzzy system and genetic algorithms,

    E. Xidias, V . Moulianitis, and P. Azariadis, “Optimal robot task schedul- ing based on adaptive neuro-fuzzy system and genetic algorithms,”The International Journal of Advanced Manufacturing Technology, vol. 115, no. 3, pp. 927–939, 07 2021, copyright - © Springer-Verlag London Ltd., part of Springer Nature 2020; Last updated - 2023-11-25

    work page 2021

  9. [9]

    Affordance wayfields for task and motion planning,

    T. McMahon, O. C. Jenkins, and N. Amato, “Affordance wayfields for task and motion planning,” in2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018, pp. 2955–2962

    work page 2018

  10. [10]

    An ontology- based approach towards coupling task and path planning for the sim- ulation of manipulation tasks,

    Y . Zhao, P. Fillatreau, M. H. Karray, and B. Archimede, “An ontology- based approach towards coupling task and path planning for the sim- ulation of manipulation tasks,” in2018 IEEE/ACS 15th International Conference on Computer Systems and Applications (AICCSA), 2018, pp. 1–8. JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 12

    work page 2018

  11. [11]

    General purpose task and motion planning for human-robot teams,

    L. Ant ˜ao, N. Costa, and G. Gonc ¸alves, “General purpose task and motion planning for human-robot teams,” in2022 2nd International Conference on Robotics, Automation and Artificial Intelligence (RAAI), 2022, pp. 8– 14

    work page 2022

  12. [12]

    Wang and W

    H. Wang and W. Chen,Simulated Annealing Algorithms for the Het- erogeneous Robots Task Scheduling Problem in Heterogeneous Robotic Order Fulfillment Systems. Springer, 01 2022, pp. 276–287

    work page 2022

  13. [13]

    Task scheduling for heterogeneous agents pickup and delivery using recurrent open shop scheduling models,

    ——, “Task scheduling for heterogeneous agents pickup and delivery using recurrent open shop scheduling models,”Robotics and Autonomous Systems, vol. 172, p. 104604, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0921889023002439

    work page 2024

  14. [14]

    A general task and motion planning framework for multiple manipulators,

    T. Pan, A. M. Wells, R. Shome, and L. E. Kavraki, “A general task and motion planning framework for multiple manipulators,” in2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021, pp. 3168–3174

    work page 2021

  15. [15]

    Multi- robot task and motion planning with subtask dependencies,

    J. Motes, R. Sandstr ¨om, H. Lee, S. Thomas, and N. M. Amato, “Multi- robot task and motion planning with subtask dependencies,”IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 3338–3345, 2020

    work page 2020

  16. [16]

    Semantic knowledge-based hierarchical planning approach for multi-robot sys- tems,

    S. Bae, S. Joo, J. Choi, J. Pyo, H. Park, and T. Kuc, “Semantic knowledge-based hierarchical planning approach for multi-robot sys- tems,”Electronics, vol. 12, no. 9, 2023

    work page 2023

  17. [17]

    Robust and safe task- driven planning and navigation for heterogeneous multi-robot teams with uncertain dynamics,

    T. Pan, C. K. Verginis, and L. E. Kavraki, “Robust and safe task- driven planning and navigation for heterogeneous multi-robot teams with uncertain dynamics,” in2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024, pp. 3482–3489

    work page 2024

  18. [18]

    Extending task and motion planning with feasibility prediction: Towards multi-robot manipulation planning of realistic objects,

    S. A. Bouhsain, R. Alami, and T. Sim ´eon, “Extending task and motion planning with feasibility prediction: Towards multi-robot manipulation planning of realistic objects,” in2024 IEEE/RSJ International Confer- ence on Intelligent Robots and Systems (IROS), 2024, pp. 10 318–10 325

    work page 2024

  19. [19]

    Probabilistic roadmaps for path planning in high-dimensional configuration spaces,

    L. Kavraki, P. Svestka, J.-C. Latombe, and M. Overmars, “Probabilistic roadmaps for path planning in high-dimensional configuration spaces,” IEEE Transactions on Robotics and Automation, vol. 12, no. 4, pp. 566– 580, 1996

    work page 1996

  20. [20]

    Rapidly-exploring random trees : a new tool for path planning,

    S. M. LaValle, “Rapidly-exploring random trees : a new tool for path planning,”The annual research report, 1998

    work page 1998

  21. [21]

    A unified sampling-based approach to integrated task and motion planning,

    W. Thomason and R. Knepper, “A unified sampling-based approach to integrated task and motion planning,” 06 2019

    work page 2019

  22. [22]

    Benchmark of sampling based motion planners in bin picking manipulation task,

    S. Realpe, F. G. Roldan, J. M. Fajardo, J. D. Hern ´andez, and P.- F. Cardenas, “Benchmark of sampling based motion planners in bin picking manipulation task,” in2022 27th International Conference on Automation and Computing (ICAC), 2022, pp. 1–6

    work page 2022

  23. [23]

    Guided sampling-based motion planning with dynamics in unknown environments,

    A. Khanal, H.-D. Bui, G. J. Stein, and E. Plaku, “Guided sampling-based motion planning with dynamics in unknown environments,” 2023

    work page 2023

  24. [24]

    idb-rrt: Sampling-based kinodynamic motion planning with motion primitives and trajectory optimization,

    J. Ortiz-Haro, W. H ¨onig, V . N. Hartmann, M. Toussaint, and L. Righetti, “idb-rrt: Sampling-based kinodynamic motion planning with motion primitives and trajectory optimization,” 2024

    work page 2024

  25. [25]

    A dataset generation tool for deep learning-based motion planning in complex environments,

    M. U. Sarwar, M. Sohail, M. U. Din, J. Rosell, and W. M. Qazi, “A dataset generation tool for deep learning-based motion planning in complex environments,” in2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ), 2021, pp. 1–4

    work page 2021

  26. [26]

    Conventional, heuristic and learning-based robot motion planning: Reviewing frameworks of current practical significance,

    F. Noroozi, M. Daneshmand, and P. Fiorini, “Conventional, heuristic and learning-based robot motion planning: Reviewing frameworks of current practical significance,”Machines, vol. 11, no. 7, 2023

    work page 2023

  27. [27]

    Multi-point path planning for robots based on deep reinforce- ment learning,

    Z. Fan, “Multi-point path planning for robots based on deep reinforce- ment learning,”Journal of Physics: Conference Series, vol. 2580, no. 1, p. 012048, sep 2023

    work page 2023

  28. [28]

    OctoMap: An efficient probabilistic 3D mapping framework based on octrees,

    A. Hornung, K. M. Wurm, M. Bennewitz, C. Stachniss, and W. Burgard, “OctoMap: An efficient probabilistic 3D mapping framework based on octrees,”Autonomous Robots, 2013

    work page 2013

  29. [29]

    A novel framework to improve motion planning of robotic systems through semantic knowledge-based reasoning,

    R. Bernardo, J. M. Sousa, and P. J. Gonc ¸alves, “A novel framework to improve motion planning of robotic systems through semantic knowledge-based reasoning,”Computers & Industrial Engineering, vol. 182, p. 109345, 2023

    work page 2023

  30. [30]

    What is yolov8? the ultimate guide,

    F. Jacob Solawetz, “What is yolov8? the ultimate guide,” https://blog. roboflow.com/whats-new-in-yolov8/, 2024, accessed:5 September 2024

    work page 2024

  31. [31]

    Multi- robot task planning for efficient battery disassembly in electric vehicles,

    C. Erdogan, C. A. Contreras, R. Stolkin, and A. Rastegarpanah, “Multi- robot task planning for efficient battery disassembly in electric vehicles,” Robotics, vol. 13, no. 5, 2024

    work page 2024

  32. [32]

    Technoeconomic assessment of electric vehicle battery disassembly-challenges and opportunities from a robotics perspective,

    J. Hathaway, C. A. Contreras, M. E. Asif, R. Stolkin, and A. Raste- garpanah, “Technoeconomic assessment of electric vehicle battery disassembly-challenges and opportunities from a robotics perspective,” IEEE Access, vol. 13, pp. 716–733, 2025

    work page 2025

  33. [33]

    Task-aware motion planning in constrained environments using gmm-informed rrt planners,

    A. Shaarawy, A. Rastegarpanah, and R. Stolkin, “Task-aware motion planning in constrained environments using gmm-informed rrt planners,” Robotics and Computer-Integrated Manufacturing, vol. 97, p. 103095, 2026

    work page 2026

  34. [34]

    Towards reuse and recycling of lithium-ion batteries: Tele-robotics for disassembly of electric vehicle batteries,

    J. Hathaway, A. Shaarawy, C. Akdeniz, A. Aflakian, R. Stolkin, and A. Rastegarpanah, “Towards reuse and recycling of lithium-ion batteries: Tele-robotics for disassembly of electric vehicle batteries,”Frontiers in Robotics and AI, vol. 10, p. 1179296, 2023

    work page 2023

  35. [35]

    The Open Motion Planning Library,

    I. A. S ¸ucan, M. Moll, and L. E. Kavraki, “The Open Motion Planning Library,”IEEE Robotics & Automation Magazine, vol. 19, no. 4, pp. 72–82, December 2012

    work page 2012

  36. [36]

    Vision-guided mpc for robotic path following using learned memory-augmented model,

    A. Rastegarpanah, J. Hathaway, and R. Stolkin, “Vision-guided mpc for robotic path following using learned memory-augmented model,” Frontiers in Robotics and AI, vol. 8, p. 688275, 2021

    work page 2021

  37. [37]

    An application of the singular value decomposition to manipulability and sensitivity of industrial robots,

    M. Togai, “An application of the singular value decomposition to manipulability and sensitivity of industrial robots,”SIAM Journal on Algebraic Discrete Methods, vol. 7, no. 2, pp. 315–320, 1986. Abdelaziz Shaarawyis a PhD candidate at the Extreme Robotics Lab, University of Birmingham. He received his B.Sc. degree in Mechatronics from Nile University, an...

    work page 1986