Deep Structured Reactive Planning

TL;DR

This paper introduces a deep structured reactive planning model for self-driving cars that jointly reasons about its own actions and other actors' reactions, improving maneuver success rates in complex traffic scenarios.

Contribution

It proposes a novel energy-based deep structured model that integrates planning and prediction for reactive decision-making in autonomous driving.

Findings

Outperforms non-reactive models in complex maneuvers

Faster completion of lane merges and turns

Maintains low collision rates

Abstract

An intelligent agent operating in the real-world must balance achieving its goal with maintaining the safety and comfort of not only itself, but also other participants within the surrounding scene. This requires jointly reasoning about the behavior of other actors while deciding its own actions as these two processes are inherently intertwined - a vehicle will yield to us if we decide to proceed first at the intersection but will proceed first if we decide to yield. However, this is not captured in most self-driving pipelines, where planning follows prediction. In this paper we propose a novel data-driven, reactive planning objective which allows a self-driving vehicle to jointly reason about its own plans as well as how other actors will react to them. We formulate the problem as an energy-based deep structured model that is learned from observational data and encodes both the planning and prediction problems. Through simulations based on both real-world driving and synthetically generated dense traffic, we demonstrate that our reactive model outperforms a non-reactive variant in successfully completing highly complex maneuvers (lane merges/turns in traffic) faster, without trading off collision rate.