A Human-Centric Method for Generating Causal Explanations in Natural Language for Autonomous Vehicle Motion Planning

06/17/2022
by   Balint Gyevnar, et al.
0

Inscrutable AI systems are difficult to trust, especially if they operate in safety-critical settings like autonomous driving. Therefore, there is a need to build transparent and queryable systems to increase trust levels. We propose a transparent, human-centric explanation generation method for autonomous vehicle motion planning and prediction based on an existing white-box system called IGP2. Our method integrates Bayesian networks with context-free generative rules and can give causal natural language explanations for the high-level driving behaviour of autonomous vehicles. Preliminary testing on simulated scenarios shows that our method captures the causes behind the actions of autonomous vehicles and generates intelligible explanations with varying complexity.

READ FULL TEXT
research
07/02/2023

Effects of Explanation Specificity on Passengers in Autonomous Driving

The nature of explanations provided by an explainable AI algorithm has b...
research
08/11/2021

Capture Uncertainties in Deep Neural Networks for Safe Operation of Autonomous Driving Vehicles

Uncertainties in Deep Neural Network (DNN)-based perception and vehicle'...
research
12/09/2020

Driving Behavior Explanation with Multi-level Fusion

In this era of active development of autonomous vehicles, it becomes cru...
research
05/05/2020

Sense-Assess-eXplain (SAX): Building Trust in Autonomous Vehicles in Challenging Real-World Driving Scenarios

This paper discusses ongoing work in demonstrating research in mobile au...
research
02/21/2023

Causal Social Explanations for Stochastic Sequential Multi-Agent Decision-Making

We present a novel framework to generate causal explanations for the dec...
research
06/21/2020

To Explain or Not to Explain: A Study on the Necessity of Explanations for Autonomous Vehicles

Explainable AI, in the context of autonomous systems, like self driving ...
research
09/28/2022

From Specification Models to Explanation Models: An Extraction and Refinement Process for Timed Automata

Autonomous systems control many tasks in our daily lives. To increase tr...

Please sign up or login with your details

Forgot password? Click here to reset