Zhihao Lin

Zhihao Lin

Ph.D. Student

Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

Safety-Critical Multi-Agent MCTS for Mixed Traffic Coordination at Unsignalized Intersections

Published in IEEE Transactions on Transactions on Intelligent Transportation Systems, 2025

This paper proposes a safety-critical multi-agent Monte Carlo tree search (MCTS) framework that integrates deterministic and probabilistic predictions to enable cooperative decision making in complex intersection scenarios.

Recommended citation: Z. Lin, et al, "Safety-Critical Multi-Agent MCTS for Mixed Traffic Coordination at Unsignalized Intersections," IEEE Trans. Intell. Transp. Syst., pp 00-00, 2025.
Download Paper

Contingency-Aware Spatiotemporal Optimization for Safe Autonomous Vehicle Trajectory Planning

Published in IEEE Transactions on Transactions on Intelligent Transportation Systems, 2025

This paper presents a contingency-aware spatiotemporal optimization framework that integrates dynamic risk assessment and trajectory optimization to ensure the autonomous host vehicle (HV) achieve safer, more efficient lane changes.

Recommended citation: Z. Lin, et al, "Contingency-Aware Spatiotemporal Optimization for Safe Autonomous Vehicle Trajectory Planning," IEEE Trans. Intell. Transp. Syst., pp 00-00, 2025.
Download Paper | View Project

KAN-LSTM Enhanced Multi-Agent Advantage Actor-Critic Reinforcement Learning for Autonomous Ramp Merging Permalink

Published in IEEE Transactions on Vehicular Technology, 2025

This paper proposes a novel KL-MA2C framework, which integrates Kolmogorov-Arnold Networks (KAN) and Long Short-Term Memory (LSTM) into the Multi-Agent Advantage Actor-Critic (MA2C) algorithm.

Recommended citation: Z. Lin, et al, "KAN-LSTM Enhanced Multi-Agent Advantage Actor-Critic Reinforcement Learning for Autonomous Ramp Merging," IEEE Trans. Veh. Technol., pp 01-12, 2025.
Download Paper

SLAM2: Simultaneous Localization and Multimode Mapping for indoor dynamic environments Permalink

Published in Pattern Recognition, 2025

we present SLAM^2, a novel semantic RGB-D SLAM system that can obtain accurate estimation of the camera pose and the 6DOF pose of other objects, resulting in complete and clean static 3D model mapping in dynamic environments.

Recommended citation: Z. Lin, Q. Zhang, Z. Tian, et al., "SLAM2: Simultaneous Localization and Multimode Mapping for indoor dynamic environments," Pattern Recognit., vol. 158, p. 111054, 2025.
Download Paper | View Project

Efficient and balanced exploration-driven decision making for autonomous racing using local information Permalink

Published in IEEE Transactions on Intelligent Vehicles, 2024

To solve traditional limitions on DRL, this paper develops an improved PPO by introducing a curiosity mechanism, a balanced reward function, and an image efficient actor-critic network.

Recommended citation: Z. Tian, et al, "Efficient and balanced exploration-driven decision making for autonomous racing using local information," IEEE Trans. Intell. Veh.,pp 1-17, 2024.
Download Paper

A conflicts-free, speed-lossless KAN-based reinforcement learning decision system for interactive driving in roundabouts Permalink

Published in arXiv preprint arXiv:2408.08242, 2024

The proposed algorithm employs a deep Q-learning network to effectively learn safe and efficient driving strategies in complex multi-vehicle roundabouts

Recommended citation: Z. Lin, et al, "A conflicts-free, speed-lossless KAN-based reinforcement learning decision system for interactive driving in roundabouts," arXiv preprint arxiv:2408.08242, 2024.
Download Paper | View Project

DPL-SLAM: enhancing dynamic point-line SLAM through dense semantic methods Permalink

Published in IEEE Sensors Journal, 2024

This paper presents a novel SLAM system, Semantic Point and Line Features SLAM (DPL-SLAM). By using dection algorithm and LK flow constrains, our proposed SLAM framework can handle dynamic environments and can be used for real-time operation.

Recommended citation: Z. Lin, Q. Zhang, Z. Tian, P. Yu, and J. Lan, "DPL-SLAM: Enhancing Dynamic Point-Line SLAM Through Dense Semantic Methods," IEEE Sens. J., vol. 24, no. 9, pp. 14596-14607, 2024.
Download Paper | View Project

Conference Papers

Balanced reward-inspired reinforcement learning for autonomous vehicle racing

Published in 6th Annual Learning for Dynamics & Control Conference, 2024

Simulation results on a physical engine demonstrate that the proposed algorithm outperforms other DRL algorithms in achieving safer control during sharp bends, fewer collisions into track boundaries, and higher training quality among multiple tracks.

Recommended citation: T. Zhen, D. Zhao, Z. Lin, et al., "Balanced reward-inspired reinforcement learning for autonomous vehicle racing," in Proc. L4DC., 2024, pp. 628-640.
Download Paper