Deep Structured Reactive Planning

01/18/2021
by   Jerry Liu, et al.
0

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.

READ FULL TEXT

page 5

page 14

page 15

research
07/01/2022

Comprehensive Reactive Safety: No Need For A Trajectory If You Have A Strategy

Safety guarantees in motion planning for autonomous driving typically in...
research
02/05/2021

Risk-Constrained Interactive Safety under Behavior Uncertainty for Autonomous Driving

Balancing safety and efficiency when planning in dense traffic is challe...
research
05/26/2021

SimNet: Learning Reactive Self-driving Simulations from Real-world Observations

In this work, we present a simple end-to-end trainable machine learning ...
research
08/09/2022

Analyzing and Enhancing Closed-loop Stability in Reactive Simulation

Simulation has played an important role in efficiently evaluating self-d...
research
05/19/2023

MR-IDM – Merge Reactive Intelligent Driver Model: Towards Enhancing Laterally Aware Car-following Models

This paper discusses the limitations of existing microscopic traffic mod...
research
08/13/2020

DSDNet: Deep Structured self-Driving Network

In this paper, we propose the Deep Structured self-Driving Network (DSDN...
research
09/14/2021

Reactive and Safe Road User Simulations using Neural Barrier Certificates

Reactive and safe agent modelings are important for nowadays traffic sim...

Please sign up or login with your details

Forgot password? Click here to reset