AURA: Asymptotically Optimal Uncertainty-Robust Replanning Algorithm for Kinodynamic Systems

Constantinos Chamzas; Donghyung Lee; Seyedali Golestaneh; Zhuoyun Zhong

arxiv: 2605.27699 · v1 · pith:AC4A53J7new · submitted 2026-05-26 · 💻 cs.RO

AURA: Asymptotically Optimal Uncertainty-Robust Replanning Algorithm for Kinodynamic Systems

Seyedali Golestaneh , Zhuoyun Zhong , Donghyung Lee , Constantinos Chamzas This is my paper

Pith reviewed 2026-06-29 16:37 UTC · model grok-4.3

classification 💻 cs.RO

keywords motion planningkinodynamic systemsreplanningmotion uncertaintyasymptotically optimalsampling-based plannerscontrol optimizationtrajectory tracking

0 comments

The pith

AURA is an asymptotically optimal meta-planner that refines trajectories online and optimizes controls to improve tracking under motion uncertainty.

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

The paper presents AURA as a framework that addresses offline computation and poor tracking in sampling-based kinodynamic planners. It runs a continuous replanning thread during execution to explore and improve the trajectory in real time. The framework also applies an optimization step to future control inputs that reduces deviations caused by motion uncertainty. A sympathetic reader would care because this combination lets planners deliver higher-quality paths that are actually followed more accurately when uncertainty is present.

Core claim

AURA is an asymptotically-optimal meta-planner framework that improves both path quality and tracking performance during execution by combining continuous replanning and control optimization under motion uncertainty. In addition to the main execution thread, this framework comprises a replanning method that continuously explores the state space and refines the trajectory during execution, and an optimization process that refines future control inputs to reduce tracking error. The proposed approach is evaluated in both simulation and real-world environments across multiple systems, demonstrating consistent improvements in trajectory quality, tracking accuracy, and overall performance compared

What carries the argument

The meta-planner framework that runs a replanning thread alongside execution and pairs it with control-input optimization to reduce tracking error.

If this is right

Trajectory quality continues to improve while the system is moving.
Tracking error decreases because future controls are adjusted for uncertainty.
The same asymptotically optimal guarantees of the underlying sampler remain available during online use.
Performance gains appear across multiple kinodynamic systems in both simulation and hardware.

Where Pith is reading between the lines

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

The same structure could be applied to other sampling-based kinodynamic planners without changing their core sampling logic.
If uncertainty statistics are known in advance, the control optimization step might be tuned once per robot rather than per task.
Real-time replanning may also help when new obstacles appear after the initial plan is made.

Load-bearing premise

The replanning thread can continuously explore the state space and refine the trajectory in real time without violating computational limits or losing the asymptotic optimality property.

What would settle it

A run in which the replanning thread fails to produce a measurably better trajectory or lower tracking error than a single offline plan computed before execution begins.

read the original abstract

Sampling-based motion planners offer a practical and scalable approach to kinodynamic motion planning, notably for high-dimensional, underactuated, or non-holonomic systems. However, these planners are typically used offline, requiring execution to begin only after the trajectory has been computed. In addition, the planned trajectory may not be accurately tracked in the presence of motion uncertainty, leading to deviations from the nominal solution. In this work, these limitations were addressed within a unified framework, \method, an asymptotically-optimal meta-planner framework that improves both path quality and tracking performance during execution. In addition to the main execution thread, this framework comprises a replanning method that continuously explores the state space and refines the trajectory during execution, and an optimization process that refines future control inputs to reduce tracking error. Together, these components enable \method to leverage asymptotically optimal planning online while improving execution accuracy under uncertainty. The proposed approach is evaluated in both simulation and real-world environments across multiple systems, demonstrating consistent improvements in trajectory quality, tracking accuracy, and overall performance compared with baseline methods.

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

AURA adds parallel replanning and control optimization to sampling-based kinodynamic planning for online use under uncertainty, but the claim that this keeps asymptotic optimality intact under real-time limits is the part that still needs verification.

read the letter

The paper's core move is to wrap a standard asymptotically optimal kinodynamic planner inside a meta-framework that keeps a replanning thread and a separate control-optimization thread running during execution. The replanning thread keeps sampling and refining the trajectory on the fly, while the optimization thread adjusts future controls to shrink tracking error caused by motion uncertainty. They report better path quality and lower tracking deviation than baselines in both simulation and hardware tests on several systems.

That combination is the concrete contribution. It turns an offline planner into something that can start executing sooner and correct itself without waiting for a full new plan. The empirical section shows consistent gains across the tested platforms, which is useful data for anyone who has tried to close the loop between sampling-based planning and real hardware.

The soft spot is the theoretical part the stress-test note flags. Asymptotic optimality proofs for planners like RRT* rely on the sample count going to infinity without hard time cutoffs. Inserting bounded replanning cycles plus an uncertainty-aware control layer adds finite-horizon effects and possible bias that the classic arguments do not automatically absorb. The abstract gives no indication of how those effects are bounded or compensated, so the central optimality claim rests on whether the full paper supplies a corrected argument or just assumes the property carries over.

This is for groups that already use sampling-based kinodynamic planners and need to move them online while dealing with model mismatch. A reader who cares about practical deployment will find the implementation choices and the hardware results worth looking at. The work is coherent enough on its own terms to merit a serious referee, even if the optimality preservation argument will probably need tightening.

Referee Report

2 major / 2 minor

Summary. The paper introduces AURA, an asymptotically optimal meta-planner for kinodynamic systems that augments sampling-based planning with a continuous replanning thread (exploring the state space during execution) and a separate control-optimization layer to reduce tracking error under motion uncertainty. It claims that this unified online framework improves both trajectory quality and execution accuracy relative to offline baselines, with supporting results from simulation and real-robot experiments across multiple systems.

Significance. If the asymptotic-optimality claim under real-time replanning holds, the work would provide a practical route to deploying sampling-based kinodynamic planners online while mitigating uncertainty-induced tracking failures, addressing a long-standing gap between theoretical guarantees and deployable performance.

major comments (2)

[§4, Theorem 2] §4 (Theoretical Analysis), Theorem 2: The argument that continuous replanning preserves asymptotic optimality relies on the number of samples tending to infinity, but does not derive an explicit bound on the truncation bias or convergence rate introduced by the fixed-time replanning cycles; standard RRT*-style proofs do not automatically extend without additional assumptions on the exploration schedule.
[§5.2] §5.2 (Experimental Setup): The reported improvements in path quality and tracking error are shown against offline baselines, but the evaluation does not include a direct comparison against other real-time replanning methods that also target asymptotic optimality (e.g., anytime or incremental variants), leaving open whether the observed gains stem from the uncertainty-robust layer or from the replanning mechanism itself.

minor comments (2)

[§3, §4.1] Notation for the uncertainty model (e.g., the distribution over disturbances) is introduced in §3 but not consistently referenced in the algorithm pseudocode of §4.1; adding a single cross-reference would improve readability.
[Figure 4] Figure 4 (real-robot trajectories) lacks error bars or multiple-run overlays; adding these would make the claimed tracking improvements easier to assess visually.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments on our manuscript. We address each major comment below, proposing revisions where the points identify gaps in the current presentation or evaluation.

read point-by-point responses

Referee: [§4, Theorem 2] §4 (Theoretical Analysis), Theorem 2: The argument that continuous replanning preserves asymptotic optimality relies on the number of samples tending to infinity, but does not derive an explicit bound on the truncation bias or convergence rate introduced by the fixed-time replanning cycles; standard RRT*-style proofs do not automatically extend without additional assumptions on the exploration schedule.

Authors: We agree that the proof of Theorem 2 extends the standard RRT* limit argument to the online setting by observing that the replanning thread continues sampling over infinite execution time, but does not supply an explicit bound on truncation bias from finite replanning cycles or a convergence rate. Additional assumptions on the exploration schedule would indeed be required for a fully rigorous extension. In the revised manuscript we will insert a clarifying remark stating these limitations and the necessary assumptions, without claiming a new rate result. revision: partial
Referee: [§5.2] §5.2 (Experimental Setup): The reported improvements in path quality and tracking error are shown against offline baselines, but the evaluation does not include a direct comparison against other real-time replanning methods that also target asymptotic optimality (e.g., anytime or incremental variants), leaving open whether the observed gains stem from the uncertainty-robust layer or from the replanning mechanism itself.

Authors: The referee correctly notes that the experiments compare AURA primarily to offline planners. While the uncertainty-robust optimization layer is the central novel element for tracking performance, the absence of online anytime or incremental baselines leaves the source of the gains partially ambiguous. We will add at least one such comparison (or a targeted discussion if space is constrained) in the revised experimental section to better isolate the contribution of the optimization layer. revision: yes

Circularity Check

0 steps flagged

No circularity detected; claims rest on external sampling-based planner properties without self-referential reduction

full rationale

The provided abstract and description introduce AURA as a meta-planner combining continuous replanning and control optimization to achieve asymptotic optimality online under uncertainty. No equations, parameter fits, or derivations are present. The asymptotic optimality is attributed to the underlying sampling-based kinodynamic planner (standard external result), with the framework described as extending it via additional threads; no self-definition, fitted-input-as-prediction, or load-bearing self-citation chain reduces the central claim to its own inputs by construction. The paper is self-contained as an algorithmic proposal with empirical evaluation.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review supplies no explicit free parameters, axioms, or invented entities; standard motion-planning assumptions such as bounded uncertainty and real-time feasibility are implicitly required but not stated.

pith-pipeline@v0.9.1-grok · 5730 in / 1000 out tokens · 32260 ms · 2026-06-29T16:37:44.421834+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

30 extracted references · 6 canonical work pages

[1]

Sampling-based motion p lanning: A comparative review,

A. Orthey, C. Chamzas, and L. E. Kavraki, “ Sampling-based motion p lanning: A comparative review,” Annual Review o f Control, Robot., and Autom. Syst., v ol. 7, no. 1, pp. 285–310, 2024. https://doi.org/10.1146/annurev-control-061623-094742

work page doi:10.1146/annurev-control-061623-094742 2024
[2]

Asymptotically optimal sampling-based motion planning methods,

J. D. Gammell and M. P. Strub, “Asymptotically optimal sampling-based motion planning methods,” Annual Review of Control, Robot., and Autom. Syst., vol. 4, no. 1, pp. 295–318, 2021

2021
[3]

Real-time adaptive motion planning (ramp) of mobile manipulators in dynamic environments with unforeseen changes,

J. Vannoy and J. Xiao, “Real-time adaptive motion planning (ramp) of mobile manipulators in dynamic environments with unforeseen changes,” IEEE Trans. Robot., vol. 24, no. 5, pp. 1199–1212, 2008

2008
[4]

Rrt x: Real-time motion planning/replanning for environments with unpredictable obstacles,

M. Otte and E. Frazzoli, “Rrt x: Real-time motion planning/replanning for environments with unpredictable obstacles,” in Algorithmic Foundations of Robotics XI. Springer, 2015, pp. 461–478

2015
[5]

Kraft: Sampling-based kinodynamic replanning and feedback control over approximate, identified models of vehicular systems,

A. Sivaramakrishnan, S. Tangirala, D. M. Ramesh, E. Granados, and K. E. Bekris, “Kraft: Sampling-based kinodynamic replanning and feedback control over approximate, identified models of vehicular systems,” arXiv preprint arXiv:2409.11522, 2024

work page arXiv 2024
[6]

Asymptotically optimal sampling- based kinodynamic planning,

Y . Li,Z. Littlefield, and K. E. Bekris, “Asymptotically optimal sampling- based kinodynamic planning,”I ntl. J. of Robotics Research, vol. 35, no. 5, pp. 528–564, 2016

2016
[7]

Model predictive heuristic control,

J. Richalet, A. Rault, J. Testud, and J. Papon, “Model predictive heuristic control,” Automatica (journal of IFAC), vol. 14, no. 5, pp. 413–428, 1978

1978
[8]

Zhou and J

K. Zhou and J. C. Doyle, Essentials of robust control. Prentice hall Upper Saddle River, NJ, 1998, vol. 104

1998
[9]

Disturbance-observer-based control and related me thods— an o verview,

W.-H. Chen, J. Yang, L. Guo, and S. Li, “ Disturbance-observer-based control and related me thods— an o verview,”I EEE Transactions on Industrial Electronics, vol. 63, no. 2, pp. 1083–1095, 2015

2015
[10]

Coarse-to-

S. Kleff, A. Meduri, R. Budhiraja, N. Mansard, and L. Righetti, “High-frequency nonlinear model predictive control of a manipulator,” in IEEE Intl. Conf. Robot. Autom., 2021, p. 7 330–7336. https: //doi.org/10.1109/ICRA48506.2021.9560990

work page doi:10.1109/icra48506.2021.9560990 2021
[11]

Asymptotically optimal planning by feasible kinodynamic planning in a s tate–cost space,

K. Hauser and Y .Zhou, “Asymptotically optimal planning by feasible kinodynamic planning in a s tate–cost space,”I EEE Trans. Robot., vol. 32, no. 6, pp. 1431–1443, 2016

2016
[12]

S. M. L aValle, Planning Algorithms. Cambridge, U.K.: Cambridge University Press, 2006

2006
[13]

A sampling-based tree p lanner f or systems with complex dynamics,

I. A. Sucan and L. E. Kavraki, “A sampling-based tree p lanner f or systems with complex dynamics,”I EEE Trans. Robot., vol. 28, no. 1, pp. 116–131, 2011

2011
[14]

Randomized kinodynamic planning,

S. M. LaValle and J. J. Kuffner Jr, “Randomized kinodynamic planning,” Intl. J. of Robotics Research, vol. 20, no. 5, pp. 378–400, 2001

2001
[15]

Path planning in expansive configuration spaces

D. Hsu, J.-C. Latombe, R. Motwani, and P. Agarwal, “Path planning in expansive configuration spaces.”I ntl. J. of Computational Geometry & Applications, vol. 9, 1999

1999
[16]

Replanning: A powerful planning strategy for hard kinodynamic problems,

K. I. T sianos and L. E. Kavraki, “Replanning: A powerful planning strategy for hard kinodynamic problems,” in IEEE/RSJ Intl. Conf. on Intell. Robots and Syst.IEEE, 2008, pp. 1667–1672

2008
[17]

Real-time adap tive non -holonomic mo tion planning in unforeseen dynamic environments,

S. McLeod and J. Xi ao, “Real-time adap tive non -holonomic mo tion planning in unforeseen dynamic environments,” in IEEE/RSJ Intl. Conf. on Intell. Robots and Syst., 2016, pp. 4692–4699

2016
[18]

Receding horizon control of nonlinear systems,

D. Mayne and H . Michalska, “Receding horizon control of nonlinear systems,”I EEE Trans. on Automatic Control, vol. 35, no. 7, pp. 814–824, 1990

1990
[19]

Model predictive control for complicated dynamic systems: a survey,

Y .Song, B. Zhang, C. Wen, D. Wang, and G. Wei, “Model predictive control for complicated dynamic systems: a survey,”International Journal of Systems Science, vol. 56, no. 9, pp. 2168–2193, 2025

2025
[20]

Differentiable robust model predictive control,

A. Oshin, H. Almubarak, and E. A. Theodorou, “Differentiable robust model predictive control,”Robotics: Science and Syst., 2024

2024
[21]

Aggressive driving with model predictive path integral control,

G . Williams, P. Drews, B. Goldfain, J. M. Rehg, and E. A. Theodorou, “Aggressive driving with model predictive path integral control,” in IEEE Intl. Conf. Robot. Autom.IEEE, 2016, pp. 1433–1440

2016
[22]

Tube-based robust nonlinear model predictive con trol1,

D. Q. Mayne and E . C. Kerrigan, “Tube-based robust nonlinear model predictive con trol1,”I FAC P roceedings Volumes, vol. 40, no. 1 2, pp. 36–41, 2007

2007
[23]

An mpc framework for efficient navigation o f mobile robots in c luttered environments,

J. K¨ohler, D. Zhang, R. Soloperto, A. Carron, and M. Zeilinger, “An mpc framework for efficient navigation o f mobile robots in c luttered environments,”arXiv preprint arXiv:2509.15917, 2025

work page arXiv 2025
[24]

Kinematics equations for differential drive and a rticulated steering,

T. Hellstr¨om, “Kinematics equations for differential drive and a rticulated steering,” 2011. https://api.semanticscholar.org/CorpusID:60171842

2011
[25]

Activepusher: Active learning and planning with residual physics for nonprehensile manipulation,

Z. Zhong, S. Golestaneh, and C. Chamzas, “Activepusher: Active learning and planning with residual physics for nonprehensile manipulation,” in IEEE Intl. Conf. Robot. Autom., 2026

2026
[26]

Mujoco: A physics engine for model- based control,

E. Todorov, T. Erez, and Y . Tassa, “Mujoco: A physics engine for model- based control,” in IEEE/RSJ Intl. Conf. on Intell. Robots and S yst., 2012, pp. 5026–5033

2012
[27]

MuSHR: A low-cost, open-source robotic racecar for education and research,

S. S. Srinivasa, P. Lancaster, J. Michalove, M. Schmittle, C. Summers, M. Rockett, J. R. Smith, S. Chouhury, C. Mavrogiannis, and F. Sadeghi, “MuSHR: A low-cost, open-source robotic racecar for education and research,”CoRR, vol. abs/1908.08031, 2019

work page arXiv 1908
[28]

The Open Motion Planning Library,

I. A. S ¸ucan, M. Moll, and L. E. Kavraki, “The Open Motion Planning Library,”I EEE Robo tics & Automation Magazine, vol. 1 9, no. 4, pp. 72–82, December 2012, https://ompl.kavrakilab.org

2012
[29]

High-frequency replanning under uncertainty using parallel sampling-based motion planning,

W. Sun, S. Patil, and R. Alterovitz, “High-frequency replanning under uncertainty using parallel sampling-based motion planning,”I EEE Trans. Robot., vol. 31, no. 1, pp. 104–116, 2015. 9

2015
[30]

Kino-pax+: Near-optimal massively parallel kinodynamic sampling-based motion planner,

N. Perrault, Q. H. Ho, and M. Lahijanian, “Kino-pax+: Near-optimal massively parallel kinodynamic sampling-based motion planner,” arXiv preprint arXiv:2602.02846, 2026

work page arXiv 2026

[1] [1]

Sampling-based motion p lanning: A comparative review,

A. Orthey, C. Chamzas, and L. E. Kavraki, “ Sampling-based motion p lanning: A comparative review,” Annual Review o f Control, Robot., and Autom. Syst., v ol. 7, no. 1, pp. 285–310, 2024. https://doi.org/10.1146/annurev-control-061623-094742

work page doi:10.1146/annurev-control-061623-094742 2024

[2] [2]

Asymptotically optimal sampling-based motion planning methods,

J. D. Gammell and M. P. Strub, “Asymptotically optimal sampling-based motion planning methods,” Annual Review of Control, Robot., and Autom. Syst., vol. 4, no. 1, pp. 295–318, 2021

2021

[3] [3]

Real-time adaptive motion planning (ramp) of mobile manipulators in dynamic environments with unforeseen changes,

J. Vannoy and J. Xiao, “Real-time adaptive motion planning (ramp) of mobile manipulators in dynamic environments with unforeseen changes,” IEEE Trans. Robot., vol. 24, no. 5, pp. 1199–1212, 2008

2008

[4] [4]

Rrt x: Real-time motion planning/replanning for environments with unpredictable obstacles,

M. Otte and E. Frazzoli, “Rrt x: Real-time motion planning/replanning for environments with unpredictable obstacles,” in Algorithmic Foundations of Robotics XI. Springer, 2015, pp. 461–478

2015

[5] [5]

Kraft: Sampling-based kinodynamic replanning and feedback control over approximate, identified models of vehicular systems,

A. Sivaramakrishnan, S. Tangirala, D. M. Ramesh, E. Granados, and K. E. Bekris, “Kraft: Sampling-based kinodynamic replanning and feedback control over approximate, identified models of vehicular systems,” arXiv preprint arXiv:2409.11522, 2024

work page arXiv 2024

[6] [6]

Asymptotically optimal sampling- based kinodynamic planning,

Y . Li,Z. Littlefield, and K. E. Bekris, “Asymptotically optimal sampling- based kinodynamic planning,”I ntl. J. of Robotics Research, vol. 35, no. 5, pp. 528–564, 2016

2016

[7] [7]

Model predictive heuristic control,

J. Richalet, A. Rault, J. Testud, and J. Papon, “Model predictive heuristic control,” Automatica (journal of IFAC), vol. 14, no. 5, pp. 413–428, 1978

1978

[8] [8]

Zhou and J

K. Zhou and J. C. Doyle, Essentials of robust control. Prentice hall Upper Saddle River, NJ, 1998, vol. 104

1998

[9] [9]

Disturbance-observer-based control and related me thods— an o verview,

W.-H. Chen, J. Yang, L. Guo, and S. Li, “ Disturbance-observer-based control and related me thods— an o verview,”I EEE Transactions on Industrial Electronics, vol. 63, no. 2, pp. 1083–1095, 2015

2015

[10] [10]

Coarse-to-

S. Kleff, A. Meduri, R. Budhiraja, N. Mansard, and L. Righetti, “High-frequency nonlinear model predictive control of a manipulator,” in IEEE Intl. Conf. Robot. Autom., 2021, p. 7 330–7336. https: //doi.org/10.1109/ICRA48506.2021.9560990

work page doi:10.1109/icra48506.2021.9560990 2021

[11] [11]

Asymptotically optimal planning by feasible kinodynamic planning in a s tate–cost space,

K. Hauser and Y .Zhou, “Asymptotically optimal planning by feasible kinodynamic planning in a s tate–cost space,”I EEE Trans. Robot., vol. 32, no. 6, pp. 1431–1443, 2016

2016

[12] [12]

S. M. L aValle, Planning Algorithms. Cambridge, U.K.: Cambridge University Press, 2006

2006

[13] [13]

A sampling-based tree p lanner f or systems with complex dynamics,

I. A. Sucan and L. E. Kavraki, “A sampling-based tree p lanner f or systems with complex dynamics,”I EEE Trans. Robot., vol. 28, no. 1, pp. 116–131, 2011

2011

[14] [14]

Randomized kinodynamic planning,

S. M. LaValle and J. J. Kuffner Jr, “Randomized kinodynamic planning,” Intl. J. of Robotics Research, vol. 20, no. 5, pp. 378–400, 2001

2001

[15] [15]

Path planning in expansive configuration spaces

D. Hsu, J.-C. Latombe, R. Motwani, and P. Agarwal, “Path planning in expansive configuration spaces.”I ntl. J. of Computational Geometry & Applications, vol. 9, 1999

1999

[16] [16]

Replanning: A powerful planning strategy for hard kinodynamic problems,

K. I. T sianos and L. E. Kavraki, “Replanning: A powerful planning strategy for hard kinodynamic problems,” in IEEE/RSJ Intl. Conf. on Intell. Robots and Syst.IEEE, 2008, pp. 1667–1672

2008

[17] [17]

Real-time adap tive non -holonomic mo tion planning in unforeseen dynamic environments,

S. McLeod and J. Xi ao, “Real-time adap tive non -holonomic mo tion planning in unforeseen dynamic environments,” in IEEE/RSJ Intl. Conf. on Intell. Robots and Syst., 2016, pp. 4692–4699

2016

[18] [18]

Receding horizon control of nonlinear systems,

D. Mayne and H . Michalska, “Receding horizon control of nonlinear systems,”I EEE Trans. on Automatic Control, vol. 35, no. 7, pp. 814–824, 1990

1990

[19] [19]

Model predictive control for complicated dynamic systems: a survey,

Y .Song, B. Zhang, C. Wen, D. Wang, and G. Wei, “Model predictive control for complicated dynamic systems: a survey,”International Journal of Systems Science, vol. 56, no. 9, pp. 2168–2193, 2025

2025

[20] [20]

Differentiable robust model predictive control,

A. Oshin, H. Almubarak, and E. A. Theodorou, “Differentiable robust model predictive control,”Robotics: Science and Syst., 2024

2024

[21] [21]

Aggressive driving with model predictive path integral control,

G . Williams, P. Drews, B. Goldfain, J. M. Rehg, and E. A. Theodorou, “Aggressive driving with model predictive path integral control,” in IEEE Intl. Conf. Robot. Autom.IEEE, 2016, pp. 1433–1440

2016

[22] [22]

Tube-based robust nonlinear model predictive con trol1,

D. Q. Mayne and E . C. Kerrigan, “Tube-based robust nonlinear model predictive con trol1,”I FAC P roceedings Volumes, vol. 40, no. 1 2, pp. 36–41, 2007

2007

[23] [23]

An mpc framework for efficient navigation o f mobile robots in c luttered environments,

J. K¨ohler, D. Zhang, R. Soloperto, A. Carron, and M. Zeilinger, “An mpc framework for efficient navigation o f mobile robots in c luttered environments,”arXiv preprint arXiv:2509.15917, 2025

work page arXiv 2025

[24] [24]

Kinematics equations for differential drive and a rticulated steering,

T. Hellstr¨om, “Kinematics equations for differential drive and a rticulated steering,” 2011. https://api.semanticscholar.org/CorpusID:60171842

2011

[25] [25]

Activepusher: Active learning and planning with residual physics for nonprehensile manipulation,

Z. Zhong, S. Golestaneh, and C. Chamzas, “Activepusher: Active learning and planning with residual physics for nonprehensile manipulation,” in IEEE Intl. Conf. Robot. Autom., 2026

2026

[26] [26]

Mujoco: A physics engine for model- based control,

E. Todorov, T. Erez, and Y . Tassa, “Mujoco: A physics engine for model- based control,” in IEEE/RSJ Intl. Conf. on Intell. Robots and S yst., 2012, pp. 5026–5033

2012

[27] [27]

MuSHR: A low-cost, open-source robotic racecar for education and research,

S. S. Srinivasa, P. Lancaster, J. Michalove, M. Schmittle, C. Summers, M. Rockett, J. R. Smith, S. Chouhury, C. Mavrogiannis, and F. Sadeghi, “MuSHR: A low-cost, open-source robotic racecar for education and research,”CoRR, vol. abs/1908.08031, 2019

work page arXiv 1908

[28] [28]

The Open Motion Planning Library,

I. A. S ¸ucan, M. Moll, and L. E. Kavraki, “The Open Motion Planning Library,”I EEE Robo tics & Automation Magazine, vol. 1 9, no. 4, pp. 72–82, December 2012, https://ompl.kavrakilab.org

2012

[29] [29]

High-frequency replanning under uncertainty using parallel sampling-based motion planning,

W. Sun, S. Patil, and R. Alterovitz, “High-frequency replanning under uncertainty using parallel sampling-based motion planning,”I EEE Trans. Robot., vol. 31, no. 1, pp. 104–116, 2015. 9

2015

[30] [30]

Kino-pax+: Near-optimal massively parallel kinodynamic sampling-based motion planner,

N. Perrault, Q. H. Ho, and M. Lahijanian, “Kino-pax+: Near-optimal massively parallel kinodynamic sampling-based motion planner,” arXiv preprint arXiv:2602.02846, 2026

work page arXiv 2026