Active Probing with Multimodal Predictions for Motion Planning

TL;DR

This paper presents a unified framework for autonomous navigation that combines multimodal prediction, active probing, and a novel risk metric to improve decision-making under uncertainty in dynamic environments.

Contribution

It introduces a new risk metric with a closed-form solution for Gaussian mixture models and an active probing mechanism to reduce prediction ambiguity in motion planning.

Findings

Successfully navigates complex traffic scenarios with uncertain predictions

Demonstrates robustness across diverse traffic agent behavior models

Provides analytical tractability for the risk metric

Abstract

Navigation in dynamic environments requires autonomous systems to reason about uncertainties in the behavior of other agents. In this paper, we introduce a unified framework that combines trajectory planning with multimodal predictions and active probing to enhance decision-making under uncertainty. We develop a novel risk metric that seamlessly integrates multimodal prediction uncertainties through mixture models. When these uncertainties follow a Gaussian mixture distribution, we prove that our risk metric admits a closed-form solution, and is always finite, thus ensuring analytical tractability. To reduce prediction ambiguity, we incorporate an active probing mechanism that strategically selects actions to improve its estimates of behavioral parameters of other agents, while simultaneously handling multimodal uncertainties. We extensively evaluate our framework in autonomous navigation scenarios using the MetaDrive simulation environment. Results demonstrate that our active probing approach successfully navigates complex traffic scenarios with uncertain predictions. Additionally, our framework shows robust performance across diverse traffic agent behavior models, indicating its broad applicability to real-world autonomous navigation challenges. Code and videos are available at https://darshangm.github.io/papers/active-probing-multimodal-predictions/.