A Hybrid Driving Decision-Making System Integrating Markov Logic Networks and Connectionist AI
- 16 December 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 24 (3) , 3514-3527
Abstract
Connectionist artificial intelligence (AI) can power many critical tasks for connected and autonomous vehicles (CAVs). However, connectionist AI lacks interpretability and usually needs large amount of data for learning. A Markov logic network (MLN), which combines first-order logic (FOL) with statistical learning, learns weighted FOL formulas for inference. MLNs can incorporate domain expert knowledge in the form of FOL formulas to achieve data-efficient learning and transparent decision process. In this paper, we propose a hybrid driving decision-making system, which integrates a MLN module and a deep Q-network (DQN) for enhanced driving safety. The MLN module evaluates the safety of ranked actions from DQN to reduce potential collisions. A collective MLN (Co-MLN) learning algorithm is proposed and it enables CAVs collectively learn a global MLN model for safe state transitions, given distributed small amount of noisy data. A hybrid DQN-MLN learning algorithm is also developed for CAVs to collectively learn to drive in new driving environments. Simulations performed using a highway driving simulator show that the proposed Co-MLN algorithm is highly data-efficient and the learned hybrid driving system can effectively reduce collisions. In addition, the learned MLN module provides transparency for safety-critical driving decisions.Keywords
Funding Information
- Ericsson Fellowship Program through Ericsson-Carleton Partnership
- Natural Sciences and Engineering Research Council of Canada (NSERC) Collaborative Research and Training Experience (CREATE) Program for Building Trust in Connected and Autonomous Vehicles
- Government of Canada’s National Crime Prevention Strategy
- General Dynamics Mission Systems-Canad
This publication has 30 references indexed in Scilit:
- Continual learning for robotics: Definition, framework, learning strategies, opportunities and challengesInformation Fusion, 2020
- Unifying logical and statistical AI with Markov logicCommunications of the ACM, 2019
- A Dynamic Bayesian Network for Vehicle Maneuver Prediction in Highway Driving Scenarios: Framework and VerificationElectronics, 2019
- A Reinforcement Learning Approach to Autonomous Decision Making of Intelligent Vehicles on HighwaysIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2018
- An approach for robust decision making rule generation: Solving transport and logistics decision making problemsExpert Systems with Applications, 2018
- Decision-Making Framework for Autonomous Driving at Road Intersections: Safeguarding Against Collision, Overly Conservative Behavior, and Violation VehiclesIEEE Transactions on Industrial Electronics, 2018
- Decision Tree-Based Maneuver Prediction for Driver Rear-End Risk-Avoidance Behaviors in Cut-In ScenariosJournal of Advanced Transportation, 2017
- Human-level control through deep reinforcement learningNature, 2015
- General Lane-Changing Model MOBIL for Car-Following ModelsTransportation Research Record: Journal of the Transportation Research Board, 2007
- Ontology-based methods for enhancing autonomous vehicle path planningRobotics and Autonomous Systems, 2004