Offline Reinforcement Learning using Human-Aligned Reward Labeling for Autonomous Emergency Braking in Occluded Pedestrian Crossing
Authors:
- Vinal AsodiaVAVinal Asodia
- Barkin DagdaBDBarkin Dagda
- Yinglong HeYHYinglong He
- Zhenhua FengZFZhenhua Feng
- Saber FallahSFSaber Fallah
Preprint
- 19 March 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Effective leveraging of real-world driving datasets is crucial for enhancing the training of autonomous driving systems. While Offline Reinforcement Learning enables training autonomous vehicles with such data, most available datasets lack meaningful reward labels. Reward labeling is essential as it provides feedback for the learning algorithm to distinguish between desirable and undesirable behaviors, thereby improving policy performance. This paper presents a novel approach for generating human-aligned reward labels. The proposed approach addresses the challenge of absent reward signals in the real-world datasets by generating labels that reflect human judgment and safety considerations. The reward function incorporates an adaptive safety component that is activated by analyzing semantic segmentation maps, enabling the autonomous vehicle to prioritize safety over efficiency in potential collision scenarios. The proposed method is applied to an occluded pedestrian crossing scenario with varying pedestrian traffic levels, using simulation data. When the generated rewards were used to train various Offline Reinforcement Learning algorithms, each model produced a meaningful policy, demonstrating the method's viability. In addition, the method was applied to a subset of the Audi Autonomous Driving Dataset, and the reward labels were compared to human-annotated reward labels. The findings show a moderate disparity between the two reward sets, and, most interestingly, the method flagged unsafe states that the human annotator missed.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Human-Aligned Longitudinal Control for Occluded Pedestrian Crossing With Visual Attention2024
- Boosting Offline Reinforcement Learning for Autonomous Driving with Hierarchical Latent Skills2024
- AD4RL: Autonomous Driving Benchmarks for Offline Reinforcement Learning with Value-based Dataset2024
- Sim-to-Real Application of Reinforcement Learning Agents for Autonomous, Real Vehicle DriftingVehicles, 2024
- Reinforcement Learning from Simulation to Real World Autonomous Driving using Digital TwinIFAC-PapersOnLine, 2023
- Less Is More: Refining Datasets for Offline Reinforcement Learning with Reward Machines2023
- Uncertainty-Aware Model-Based Offline Reinforcement Learning for Automated DrivingIEEE Robotics and Automation Letters, 2023
- Planning for Autonomous Driving via Interaction-Aware Probabilistic Action PoliciesIEEE Access, 2022
- Crossing the Reality Gap: A Survey on Sim-to-Real Transferability of Robot Controllers in Reinforcement LearningIEEE Access, 2021
- Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey2020