Act Natural! Projecting Autonomous System Trajectories Into Naturalistic Behavior Sets

TL;DR

This paper introduces a novel method for modeling naturalistic human behavior as convex hulls and projects autonomous trajectories into these sets to enhance naturalness while respecting dynamics constraints, demonstrated on real-world driving data.

Contribution

It presents a new convex hull-based modeling approach and an optimization filter for projecting trajectories, improving naturalistic behavior in autonomous agents.

Findings

Effective projection of trajectories into naturalistic behavior sets

Demonstrated on real-world driving data from inD dataset

Improved naturalness of autonomous agent trajectories

Abstract

Autonomous agents operating around human actors must consider how their behaviors might affect those humans, even when not directly interacting with them. To this end, it is often beneficial to be predictable and appear naturalistic. Existing methods to address this problem use human actor intent modeling or imitation learning techniques, but these approaches rarely capture all possible motivations for human behavior or require significant amounts of data. In contrast, we propose a technique for modeling naturalistic behavior as a set of convex hulls computed over a relatively small dataset of human behavior. Given this set, we design an optimization-based filter which projects arbitrary trajectories into it to make them more naturalistic for autonomous agents to execute while also satisfying dynamics constraints. We demonstrate our methods on real-world human driving data from the inD intersection dataset (Bock et al., 2020).