Safe-horizon control improves motion planning with uncertain obstacle behavior
Distribution-Transfer Safe-Horizon MPC under Mode Uncertainty
Robotics
Summary
Motion planning involves steering machines like robots while avoiding obstacles, but obstacles can behave in different ways that aren’t fully known. The authors found a way to safely control movements even when the exact way obstacles move is uncertain. They use a mathematical model that guesses probabilities for different obstacle behaviors and adjust the safety checks to cover all likely scenarios. This helps the system stay safe despite not knowing precisely how obstacles will act.
What this means in practice
- •For autonomous vehicle engineers: Improve obstacle avoidance for self-driving cars when obstacle behavior is unpredictable or changes modes.
- •For robotics motion planners: Enhance safety in robot navigation by better accounting for uncertain obstacle actions in planning algorithms.
Authors
Stephen Crawford, Nora Ayanian
Abstract
Scenario-based MPC is an attractive strategy for chance-constrained motion planning that approximates uncertainty via a finite set of sampled scenarios. As a sampling-based method, scenario-based MPC is sensitive to distribution mismatch. We address this problem in the context of Safe-Horizon Model Predictive Control (SH-MPC) with obstacles governed by switching dynamic modes. From finite mode observations, we construct a confidence set for the unknown categorical mode law and derive a multiplicative domination bound that transfers a Safe-Horizon collision-risk certificate from a selected scenario-sampling distribution to every law in the confidence set. Wasserstein geometry is used to regularize probability reallocation among modes according to the similarity of their induced trajectory predictions, while a collision-risk surrogate biases sampling toward dangerous modes. The resulting certificate explicitly quantifies the additional tightening required under distribution mismatch and exposes the multiplicative conservatism that arises when several obstacle-wise transfer factors are combined