Anticipatory Navigation in Crowds by Probabilistic Prediction of Pedestrian Future Movements

TL;DR

This paper introduces SPAN, a probabilistic framework enabling robots to anticipate pedestrian movements and navigate safely in crowded environments by predicting future positions and integrating static obstacle data.

Contribution

The paper presents a novel stochastic process-based predictive model for pedestrian motion, integrated into a collision-checking and navigation framework for robots in crowds.

Findings

Effective in crowded simulations

Successful real-world pedestrian dataset validation

Improves robot safety and navigation efficiency

Abstract

Critical for the coexistence of humans and robots in dynamic environments is the capability for agents to understand each other's actions, and anticipate their movements. This paper presents Stochastic Process Anticipatory Navigation (SPAN), a framework that enables nonholonomic robots to navigate in environments with crowds, while anticipating and accounting for the motion patterns of pedestrians. To this end, we learn a predictive model to predict continuous-time stochastic processes to model future movement of pedestrians. Anticipated pedestrian positions are used to conduct chance constrained collision-checking, and are incorporated into a time-to-collision control problem. An occupancy map is also integrated to allow for probabilistic collision-checking with static obstacles. We demonstrate the capability of SPAN in crowded simulation environments, as well as with a real-world pedestrian dataset.