Probably Approximately Correct Vision-Based Planning using Motion Primitives

• Published in: arXiv.org
• Main Authors: Veer, Sushant, Majumdar, Anirudha
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 10.11.2020
• Subjects: Artificial neural networks; Computer Science - Learning; Computer Science - Robotics; Computer Science - Systems and Control; Computer simulation; Convexity; Machine learning; Mathematics - Optimization and Control; Obstacle avoidance; Optimization; Policies; Training; Unmanned aerial vehicles; Upper bounds; Vision
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.2002.12852

This paper presents an approach for learning vision-based planners that provably generalize to novel environments (i.e., environments unseen during training). We leverage the Probably Approximately Correct (PAC)-Bayes framework to obtain an upper bound on the expected cost of policies across all environments. Minimizing the PAC-Bayes upper bound thus trains policies that are accompanied by a certificate of performance on novel environments. The training pipeline we propose provides strong generalization guarantees for deep neural network policies by (a) obtaining a good prior distribution on the space of policies using Evolutionary Strategies (ES) followed by (b) formulating the PAC-Bayes optimization as an efficiently-solvable parametric convex optimization problem. We demonstrate the efficacy of our approach for producing strong generalization guarantees for learned vision-based motion planners through two simulated examples: (1) an Unmanned Aerial Vehicle (UAV) navigating obstacle fields with an onboard vision sensor, and (2) a dynamic quadrupedal robot traversing rough terrains with proprioceptive and exteroceptive sensors.