paper-with-me

홈 › Papers

Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control

2023-11-30 · Bernd Frauenknecht, Tobias Ehlgen, Sebastian Trimpe

Advanced vehicle control is a fundamental building block in the development of autonomous driving systems. Reinforcement learning (RL) promises to achieve control performance superior to classical approaches while keeping computational demands low during deployment. However, standard RL approaches like soft-actor critic (SAC) require extensive amounts of training data to be collected and are thus impractical for real-world application. To address this issue, we apply recently developed data-efficient deep RL methods to vehicle trajectory control. Our investigation focuses on three methods, so far unexplored for vehicle control: randomized ensemble double Q-learning (REDQ), probabilistic ensembles with trajectory sampling and model predictive path integral optimizer (PETS-MPPI), and model-based policy optimization (MBPO). We find that in the case of trajectory control, the standard model-based RL formulation used in approaches like PETS-MPPI and MBPO is not suitable. We, therefore, propose a new formulation that splits dynamics prediction and vehicle localization. Our benchmark study on the CARLA simulator reveals that the three identified data-efficient deep RL approaches learn control strategies on a par with or better than SAC, yet reduce the required number of environment interactions by more than one order of magnitude.

📄 PDF Abstract BibTeX arXiv:2311.18393

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingDeep Reinforcement LearningQ-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Double Q-learning Double Q-learning is an off-policy reinforcement learning algorithm that utilises double estimation to counteract overestimation problems with traditional Q-learning. The…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
Dilated Convolution 설명 없음

Similar Papers 제목 키워드 기반

Dynamics-Decoupled Trajectory Alignment for Sim-to-Real Transfer in Reinforcement Learning for Autonomous Driving

2025-11-10 · Thomas Steinecker, Alexander Bienemann, Denis Trescher, Thorsten Luettel 외 arxiv

Reinforcement learning (RL) has shown promise in robotics, but deploying RL on real vehicles remains challenging due to the complexity of vehicle dynamics and the mismatch between simulation and reality. Factors such as …

Reinforcement LearningContinuous ControlAutonomous DrivingMotion Planning

End-to-End Vision-Based Adaptive Cruise Control (ACC) Using Deep Reinforcement Learning

2020-01-24 · Zhensong Wei, Yu Jiang, Xishun Liao, Xuewei Qi 외

This paper presented a deep reinforcement learning method named Double Deep Q-networks to design an end-to-end vision-based adaptive cruise control (ACC) system. A simulation environment of a highway scene was set up in …

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

A Hybrid Input based Deep Reinforcement Learning for Lane Change Decision-Making of Autonomous Vehicle

2025-09-01 · Ziteng Gao, Jiaqi Qu, Chaoyu Chen arxiv

Lane change decision-making for autonomous vehicles is a complex but high-reward behavior. In this paper, we propose a hybrid input based deep reinforcement learning (DRL) algorithm, which realizes abstract lane change d…

Reinforcement LearningTrajectory PredictionAutonomous Vehicles

Traffic Smoothing Controllers for Autonomous Vehicles Using Deep Reinforcement Learning and Real-World Trajectory Data

2024-01-18 · Nathan Lichtlé, Kathy Jang, Adit Shah, Eugene Vinitsky 외

Designing traffic-smoothing cruise controllers that can be deployed onto autonomous vehicles is a key step towards improving traffic flow, reducing congestion, and enhancing fuel efficiency in mixed autonomy traffic. We …

Autonomous VehiclesDeep Reinforcement Learning

A Robust Fuel Optimization Strategy For Hybrid Electric Vehicles: A Deep Reinforcement Learning Based Continuous Time Design Approach

2021-01-01 · Nilanjan Mukherjee, Sudeshna Sarkar

This paper deals with the fuel optimization problem for hybrid electric vehicles in deep reinforcement learning framework. Firstly, considering the hybrid electric vehicle as an uncertain non-linear system with unknown d…

Deep Reinforcement LearningManagementreinforcement-learningReinforcement Learning+1