Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models

TL;DR

This paper introduces a learned contingency planner that uses high-dimensional observations and behavioral models to enable safe, adaptive decision-making in multi-agent scenarios like driving, outperforming noncontingent methods.

Contribution

We develop a tractable, end-to-end learned contingency planning method using autoregressive flow models for multi-agent decision-making from observational data.

Findings

Our method significantly outperforms noncontingent planning approaches.

Contingency planning improves safety and decision quality in multi-agent driving scenarios.

The approach is validated on a realistic CARLA driving benchmark.

Abstract

Humans have a remarkable ability to make decisions by accurately reasoning about future events, including the future behaviors and states of mind of other agents. Consider driving a car through a busy intersection: it is necessary to reason about the physics of the vehicle, the intentions of other drivers, and their beliefs about your own intentions. If you signal a turn, another driver might yield to you, or if you enter the passing lane, another driver might decelerate to give you room to merge in front. Competent drivers must plan how they can safely react to a variety of potential future behaviors of other agents before they make their next move. This requires contingency planning: explicitly planning a set of conditional actions that depend on the stochastic outcome of future events. In this work, we develop a general-purpose contingency planner that is learned end-to-end using high-dimensional scene observations and low-dimensional behavioral observations. We use a conditional autoregressive flow model to create a compact contingency planning space, and show how this model can tractably learn contingencies from behavioral observations. We developed a closed-loop control benchmark of realistic multi-agent scenarios in a driving simulator (CARLA), on which we compare our method to various noncontingent methods that reason about multi-agent future behavior, including several state-of-the-art deep learning-based planning approaches. We illustrate that these noncontingent planning methods fundamentally fail on this benchmark, and find that our deep contingency planning method achieves significantly superior performance. Code to run our benchmark and reproduce our results is available at https://sites.google.com/view/contingency-planning