ROLGSYOCFeb 28, 2020

Probably Approximately Correct Vision-Based Planning using Motion Primitives

arXiv:2002.12852v222 citations
AI Analysis

This addresses the challenge of ensuring reliable robot planning in unseen settings, offering a provable method for safety-critical applications, though it is incremental in applying PAC-Bayes to vision-based planning.

The paper tackles the problem of learning vision-based planners that generalize to novel environments by using the PAC-Bayes framework to provide performance certificates, achieving strong generalization guarantees in simulated examples like UAV navigation and quadrupedal robot traversal.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes