Agent-aware State Estimation in Autonomous Vehicles

TL;DR

This paper presents a new agent-aware state estimation framework for autonomous vehicles that improves global state inference by incorporating observations of other agents' behaviors, especially useful under occlusion scenarios.

Contribution

It introduces agent-aware state estimation and a scalable transition-independent subclass, enhancing multi-agent environment state inference in autonomous systems.

Findings

Higher accuracy than existing methods in traffic light classification under occlusion.

Scales linearly with the number of agents, enabling efficient inference in large environments.

Effective in real-world autonomous vehicle data scenarios.

Abstract

Autonomous systems often operate in environments where the behavior of multiple agents is coordinated by a shared global state. Reliable estimation of the global state is thus critical for successfully operating in a multi-agent setting. We introduce agent-aware state estimation -- a framework for calculating indirect estimations of state given observations of the behavior of other agents in the environment. We also introduce transition-independent agent-aware state estimation -- a tractable class of agent-aware state estimation -- and show that it allows the speed of inference to scale linearly with the number of agents in the environment. As an example, we model traffic light classification in instances of complete loss of direct observation. By taking into account observations of vehicular behavior from multiple directions of traffic, our approach exhibits accuracy higher than that of existing traffic light-only HMM methods on a real-world autonomous vehicle data set under a variety of simulated occlusion scenarios.