mlsanityData to 14 Oct 2026

Learning Provably Robust Motion Planners Using Funnel Libraries

arXiv 2111.08733 ↗First posted 16 Nov 2021cs.RO cs.LG cs.SYcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper presents an approach for learning motion planners that are accompanied with probabilistic guarantees of success on new environments that hold uniformly for any disturbance to the robot's dynamics within an admissible set. We achieve this by bringing together tools from generalization theory and robust control. First, we curate a library of motion primitives where the robustness of each primitive is characterized by an over-approximation of the forward reachable set, i.e., a "funnel". Then, we optimize probably approximately correct (PAC)-Bayes generalization bounds for training our planner to compose these primitives such that the entire funnels respect the problem specification. We demonstrate the ability of our approach to provide strong guarantees on two simulated examples: (i) navigation of an autonomous vehicle under external disturbances on a five-lane highway with multiple vehicles, and (ii) navigation of a drone across an obstacle field in the presence of wind disturbances.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 56 references that are in the map. First posted on arXiv 16 Nov 2021.

Builds on

32 of 56 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  3. 2019Solving Rubik's Cube with a Robot Handcited by 734
  4. 2017Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Datacited by 533
  5. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 436
  6. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  7. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  8. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 337
  9. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 313
  10. 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 260
  11. 2018A Study on Overfitting in Deep Reinforcement Learningcited by 174
  12. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 174
20 more
  1. 2017DARLA: Improving Zero-Shot Transfer in Reinforcement Learningcited by 149
  2. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  3. 2020CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learningcited by 109
  4. 2018The Limits and Potentials of Deep Learning for Roboticscited by 104
  5. 2018Evolved Policy Gradientscited by 88
  6. 2019Improving Generalization in Meta Reinforcement Learning using Learned Objectivescited by 68
  7. 2016Q-Learning for Robust Satisfaction of Signal Temporal Logic Specificationscited by 67
  8. 2020Backpropagation through Signal Temporal Logic Specifications: Infusing Logical Structure into Gradient-Based Methodscited by 54
  9. 2019Distributionally Robust Reinforcement Learningcited by 42
  10. 2020Distributional Robustness and Regularization in Reinforcement Learningcited by 40
  11. 2015Control Contraction Metrics: Convex and Intrinsic Criteria for Nonlinear Feedback Designcited by 39
  12. 2020Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learningcited by 37
  13. 2019PAC-Bayes with Backpropcited by 36
  14. 2016Funnel Libraries for Real-Time Robust Feedback Motion Planningcited by 29
  15. 2019JuliaReach: a Toolbox for Set-Based Reachabilitycited by 28
  16. 2018PAC-Bayes Control: Learning Policies that Provably Generalize to Novel Environmentscited by 22
  17. 2021Distributionally Robust Policy Learning via Adversarial Environment Generationcited by 17
  18. 2020Probably Approximately Correct Vision-Based Planning using Motion Primitivescited by 16
  19. 2015Monte Carlo Motion Planning for Robot Trajectory Optimization Under Uncertaintycited by 12
  20. 2018Provably Robust Learning-Based Approach for High-Accuracy Tracking Control of Lagrangian Systemscited by 10

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guaranteescited by 27