Perception as prediction using general value functions in autonomous driving applications
Authors:
- 1 November 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1202-1209
Abstract
We propose and demonstrate a framework called perception as prediction for autonomous driving that uses general value functions (GVFs) to learn predictions. Perception as prediction learns data-driven predictions relating to the impact of actions on the agent’s perception of the world. It also provides a data-driven approach to predict the impact of the anticipated behavior of other agents on the world without explicitly learning their policy or intentions. We demonstrate perception as prediction by learning to predict an agent’s front safety and rear safety with GVFs, which encapsulate anticipation of the behavior of the vehicle in front and in the rear, respectively. The safety predictions are learned through random interactions in a simulated environment containing other agents. We show that these predictions can be used to produce similar control behavior to an LQR-based controller in an adaptive cruise control problem as well as provide advanced warning when the vehicle behind is approaching dangerously. The predictions are compact policy-based predictions that support prediction of the long term impact on safety when following a given policy. We analyze two controllers that use the learned predictions in a racing simulator to understand the value of the predictions and demonstrate their use in the real-world on a Clearpath Jackal robot and an autonomous vehicle platform.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Architecture Design and Implementation of an Autonomous VehicleIEEE Access, 2018
- Adaptive Cruise Control with Safety Guarantees for Autonomous VehiclesIFAC-PapersOnLine, 2017
- Intelligent laser welding through representation, prediction, and control learning: An architecture with deep neural networks and reinforcement learningMechatronics, 2016
- Whatever next? Predictive brains, situated agents, and the future of cognitive scienceBehavioral and Brain Sciences, 2013
- Multi-timescale Nexting in a Reinforcement Learning RobotLecture Notes in Computer Science, 2012
- Online human training of a myoelectric prosthesis controller via actor-critic reinforcement learning2011
- Design and implementation of parameterized adaptive cruise control: An explicit model predictive control approachControl Engineering Practice, 2010
- A comprehensive review of the development of adaptive cruise control systemsVehicle System Dynamics, 2010
- Design, tuning, and evaluation of a full-range adaptive cruise control system with collision avoidanceControl Engineering Practice, 2009
- Learning to predict by the methods of temporal differencesMachine Learning, 1988