LORD: Large Models Based Opposite Reward Design for Autonomous Driving
Authors:
- 26 February 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5072-5081
Abstract
Reinforcement learning (RL) based autonomous driving has emerged as a promising alternative to data-driven imitation learning approaches. However, crafting effective reward functions for RL poses challenges due to the complexity of defining and quantifying good driving behaviors across diverse scenarios. Recently, large pretrained models have gained significant attention as zero-shot reward models for tasks specified with desired linguistic goals. However, the desired linguistic goals for autonomous driving such as “drive safely” are ambiguous and incomprehen-sible by pretrained models. On the other hand, undesired linguistic goals like “collision” are more concrete and tractable. In this work, we introduce LORD, a novel large models based opposite reward design through undesired linguistic goals to enable the efficient use of large pretrained models as zero-shot reward models. Through extensive experiments, our proposed framework shows its efficiency in leveraging the power of large pretrained models for achieving safe and enhanced autonomous driving. Moreover, the proposed approach shows improved generalization capabilities as it outperforms counterpart methods across diverse and challenging driving scenarios.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs2024
- VLP: Vision Language Planning for Autonomous Driving2024
- VAD: Vectorized Scene Representation for Efficient Autonomous Driving2023
- Planning-oriented Autonomous Driving2023
- BEVFormer: Learning Bird’s-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers2022
- Learning to Play Pursuit-Evasion with Visibility Constraints2021
- HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips2019
- Exploring the Limitations of Behavior Cloning for Autonomous Driving2019
- Learning to Drive in a Day2019
- Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification2018