Adaptive Conformal Prediction for Motion Planning among Dynamic Agents

TL;DR

This paper introduces an adaptive conformal prediction algorithm for motion planning among dynamic agents, providing probabilistic safety guarantees by quantifying true prediction uncertainty in real-time, demonstrated through drone navigation simulations.

Contribution

It presents a novel adaptive conformal prediction method integrated with model predictive control for safe motion planning among dynamic agents.

Findings

The algorithm achieves probabilistic coverage of predictions in dynamic environments.

It effectively captures changes in prediction quality and agent behavior.

Simulation results demonstrate safe navigation of a drone avoiding a flying frisbee.

Abstract

This paper proposes an algorithm for motion planning among dynamic agents using adaptive conformal prediction. We consider a deterministic control system and use trajectory predictors to predict the dynamic agents' future motion, which is assumed to follow an unknown distribution. We then leverage ideas from adaptive conformal prediction to dynamically quantify prediction uncertainty from an online data stream. Particularly, we provide an online algorithm uses delayed agent observations to obtain uncertainty sets for multistep-ahead predictions with probabilistic coverage. These uncertainty sets are used within a model predictive controller to safely navigate among dynamic agents. While most existing data-driven prediction approached quantify prediction uncertainty heuristically, we quantify the true prediction uncertainty in a distribution-free, adaptive manner that even allows to capture changes in prediction quality and the agents' motion. We empirically evaluate of our algorithm on a simulation case studies where a drone avoids a flying frisbee.