Counterfactual Reasoning about Intent for Interactive Navigation in Dynamic Environments

TL;DR

This paper introduces a real-time, scalable motion planning framework for autonomous robots in dynamic environments, integrating intention inference through counterfactual reasoning, efficient visual tracking, and validation in multi-robot and human-robot navigation scenarios.

Contribution

The paper presents a novel real-time motion planning approach combining counterfactual intention inference with a distributed visual tracker, scalable to dense environments without extensive offline training.

Findings

Efficient iterative planning enables fluid navigation around pedestrians.

The framework outperforms policy learning methods in dense, dynamic settings.

The visual tracker demonstrates robustness on large-scale pedestrian datasets.

Abstract

Many modern robotics applications require robots to function autonomously in dynamic environments including other decision making agents, such as people or other robots. This calls for fast and scalable interactive motion planning. This requires models that take into consideration the other agent's intended actions in one's own planning. We present a real-time motion planning framework that brings together a few key components including intention inference by reasoning counterfactually about potential motion of the other agents as they work towards different goals. By using a light-weight motion model, we achieve efficient iterative planning for fluid motion when avoiding pedestrians, in parallel with goal inference for longer range movement prediction. This inference framework is coupled with a novel distributed visual tracking method that provides reliable and robust models for the current belief-state of the monitored environment. This combined approach represents a computationally efficient alternative to previously studied policy learning methods that often require significant offline training or calibration and do not yet scale to densely populated environments. We validate this framework with experiments involving multi-robot and human-robot navigation. We further validate the tracker component separately on much larger scale unconstrained pedestrian data sets.