自动驾驶赛车带来了具有挑战性的控制问题,但模型预测控制(MPC)在解决最短圈速问题和一对一竞速方面都取得了可喜的进展。然而,基于模型的控制需要准确的系统模型,包括车辆动力学模型和对手行为模型。动力学模型误差和对手行为都可以用高斯过程(GP)回归进行建模。GP模型可以利用控制器收集的数据进行迭代更新,但GP模型的性能取决于训练数据的多样性。我们提出了一种用于迭代GP回归的新型主动探索机制,该机制有目的地在GP模型不确定性较高的区域收集额外数据。在探索过程中,MPC通过平衡竞速目标和探索准则来收集多样化数据;随后对GP进行重新训练。该过程迭代重复;在后续迭代中,探索被停用,仅优化竞速目标。因此,MPC可以利用改进后的GP模型获得更好的性能。我们在Sony Interactive Entertainment Inc的高度逼真的赛车仿真平台Gran Turismo Sport上针对最短圈速挑战验证了我们的方法,并在一对一竞速的数值仿真中进行了验证。与先前方法相比,我们的主动探索机制显著提高了GP预测精度,从而改善了竞速性能。
英文摘要:
Autonomous racing creates challenging control problems, but Model Predictive Control (MPC) has made promising steps toward solving both the minimum lap-time problem and head-to-head racing. Yet, accurate models of the system are necessary for model-based control, including models of vehicle dynamics and opponent behavior. Both dynamics model error and opponent behavior can be modeled with Gaussian Process (GP) regression. GP models can be updated iteratively from data collected using the controller, but the strength of the GP model depends on the diversity of the training data. We propose a novel active exploration mechanism for iterative GP regression that purposefully collects additional data at regions of higher uncertainty in the GP model. In the exploration, a MPC collects diverse data by balancing the racing objectives and the exploration criterion; then the GP is re-trained. The process is repeated iteratively; in later iterations, the exploration is deactivated, and only the racing objectives are optimized. Thus, the MPC can achieve better performance by leveraging the improved GP model. We validate our approach in the highly realistic racing simulation platform Gran Turismo Sport of Sony Interactive Entertainment Inc for a minimum lap time challenge, and in numerical simulation of head-to-head. Our active exploration mechanism yields a significant improvement in the GP prediction accuracy compared to previous approaches and, thus, an improved racing performance.
IteraOptiRacing: A Unified Planning-Control Framework for Real-time Autonomous Racing for Iterative Optimal Performance
Shanghai Jiao Tong University(上海交通大学);University of Pennsylvania(宾夕法尼亚大学);University of Minnesota-Twin Cities(明尼苏达大学-双城分校);University of California, Berkeley(加州大学伯克利分校)
Regulation-Aware Game-Theoretic Motion Planning for Autonomous Racing
University of Modena and Reggio Emilia(摩德纳和雷吉奥艾米利亚大学);University of Bologna(博洛尼亚大学);University of California, Berkeley(加州大学伯克利分校);Chalmers University of Technology(查尔姆斯理工大学)
Benchmarking Empirical and Learning-Based Approaches for Feedforward Steering Control in Autonomous Racing
Chair of Automatic Control, Department of Engineering Physics and Computation, Technical University of Munich(慕尼黑技术大学自动控制系);Professorship of Autonomous Vehicle Systems (AVS), Department of Mobility Systems Engineering, Technical University of Munich(慕尼黑技术大学移动系统工程系自动驾驶车辆系统教授职位)
Iterative Linear Quadratic Optimization for Nonlinear Control: Differentiable Programming Algorithmic Templates
Google Brain, Seattle, USA(谷歌大脑);Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, USA(保罗·G·艾伦计算机科学与工程学院);Department of Electrical and Computer Engineering, University of Washington, Seattle, USA(电气与计算机工程系);Department of Statistics University of Washington, Seattle, USA(统计学系)
Iterative Learning Control-Informed Reinforcement Learning for Batch Process Control
State Key Laboratory of Industrial Control Technology, Institute of Cyber-Systems and Control, Zhejiang University(工业控制技术国家重点实验室,系统与控制研究所,浙江大学);Department of Chemical Engineering, Chung-Yuan Christian University(Chung-Yuan Christian University 化学工程系)