Incorporating Human Domain Knowledge into Large Scale Cost Function Learning

12/13/2016
by   Markus Wulfmeier, et al.
0

Recent advances have shown the capability of Fully Convolutional Neural Networks (FCN) to model cost functions for motion planning in the context of learning driving preferences purely based on demonstration data from human drivers. While pure learning from demonstrations in the framework of Inverse Reinforcement Learning (IRL) is a promising approach, we can benefit from well informed human priors and incorporate them into the learning process. Our work achieves this by pretraining a model to regress to a manual cost function and refining it based on Maximum Entropy Deep Inverse Reinforcement Learning. When injecting prior knowledge as pretraining for the network, we achieve higher robustness, more visually distinct obstacle boundaries, and the ability to capture instances of obstacles that elude models that purely learn from demonstration data. Furthermore, by exploiting these human priors, the resulting model can more accurately handle corner cases that are scarcely seen in the demonstration data, such as stairs, slopes, and underpasses.

READ FULL TEXT
research
09/16/2019

Off-road Autonomous Vehicles Traversability Analysis and Trajectory Planning Based on Deep Inverse Reinforcement Learning

Terrain traversability analysis is a fundamental issue to achieve the au...
research
07/01/2022

Lifelong Inverse Reinforcement Learning

Methods for learning from demonstration (LfD) have shown success in acqu...
research
03/25/2019

Inverse Optimal Planning for Air Traffic Control

We envision a system that concisely describes the rules of air traffic c...
research
07/14/2021

Mixing Human Demonstrations with Self-Exploration in Experience Replay for Deep Reinforcement Learning

We investigate the effect of using human demonstration data in the repla...
research
05/01/2019

Driving with Style: Inverse Reinforcement Learning in General-Purpose Planning for Automated Driving

Behavior and motion planning play an important role in automated driving...
research
04/12/2020

Reinforcement Learning via Reasoning from Demonstration

Demonstration is an appealing way for humans to provide assistance to re...
research
06/09/2020

Learning Navigation Costs from Demonstration with Semantic Observations

This paper focuses on inverse reinforcement learning (IRL) for autonomou...

Please sign up or login with your details

Forgot password? Click here to reset