We present a reinforcement learning-based solution to autonomously race on a miniature race car platform. We show that a policy that is trained purely in simulation using a relatively simple vehicle model, including model randomization, can be successfully transferred to the real robotic setup. We achieve this by using novel policy output regularization approach and a lifted action space which enables smooth actions but still aggressive race car driving. We show that this regularized policy does outperform the Soft Actor Critic (SAC) baseline method, both in simulation and on the real car, but it is still outperformed by a Model Predictive Controller (MPC) state of the art method. The refinement of the policy with three hours of real-world interaction data allows the reinforcement learning policy to achieve lap times similar to the MPC controller while reducing track constraint violations by 50%.
MCTR: Midpoint Corrected Triangulation for Autonomous Racing via Digital Twin Simulation in CARLA
Department of Control Science and Engineering, Zhejiang University, Hangzhou, China（浙江大学控制科学与工程学院）；Ningbo Innovation Center, Zhejiang University, Ningbo, China（浙江大学宁波创新中心）；Center for Project-Based Learning, D-ITET, ETH Zurich（苏黎世联邦理工学院项目导向学习中心）；Technische Universität Wien, Vienna, Austria（维也纳技术大学）
本文提出 MCTR 算法，通过曲率校正移动平均改进轨迹平滑性，并在 CARLA 数字孪生中验证 3D LiDAR 感知下的自主赛车性能。
DeepRacer is a platform for end-to-end experimentation with RL and can be used to systematically investigate the key challenges in developing intelligent control systems. Using the platform, we demonstrate how a 1/18th scale car can learn to drive autonomously using RL with a monocular camera. It is trained in simulation with no additional tuning in physical world and demonstrates: 1) formulation and solution of a robust reinforcement learning algorithm, 2) narrowing the reality gap through joint perception and dynamics, 3) distributed on-demand compute architecture for training optimal polici…
The University of Manchester（曼彻斯特大学）；Oxford Brookes University（牛津布鲁克斯大学）
Widespread development of driverless vehicles has led to the formation of autonomous racing, where technological development is accelerated by the high speeds and competitive environment of motorsport. A particular challenge for an autonomous vehicle is that of identifying a target trajectory - or, in the case of a competition vehicle, the racing line. Many existing approaches to finding the racing line are either not time-optimal solutions, or are computationally expensive - rendering them unsuitable for real-time application using on-board processing hardware. This study describes a machine …
The Hong Kong University of Science and Technology（香港科技大学）
Autonomous car racing is a challenging task in the robotic control area. Traditional modular methods require accurate mapping, localization and planning, which makes them computationally inefficient and sensitive to environmental changes. Recently, deep-learning-based end-to-end systems have shown promising results for autonomous driving/racing. However, they are commonly implemented by supervised imitation learning (IL), which suffers from the distribution mismatch problem, or by reinforcement learning (RL), which requires a huge amount of risky interaction data. In this work, we present a ge…
We present an approach for safe trajectory planning, where a strategic task related to autonomous racing is learned sample-efficient within a simulation environment. A high-level policy, represented as a neural network, outputs a reward specification that is used within the cost function of a parametric nonlinear model predictive controller (NMPC). By including constraints and vehicle kinematics in the NLP, we are able to guarantee safe and feasible trajectories related to the used model. Compared to classical reinforcement learning (RL), our approach restricts the exploration to safe trajecto…
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）
Georgia Institute of Technology（佐治亚理工学院）；Twentieth Century Fox（二十世纪福克斯）；Starfleet Academy（星际舰队学院）；Tyrell Inc.（泰瑞尔公司）
A fundamental aspect of racing is overtaking other race cars. Whereas previous research on autonomous racing has majorly focused on lap-time optimization, here, we propose a method to plan overtaking maneuvers in autonomous racing. A Gaussian process is used to learn the behavior of the leading vehicle. Based on the outputs of the Gaussian process, a stochastic Model Predictive Control algorithm plans optimistic trajectories, such that the controlled autonomous race car is able to overtake the leading vehicle. The proposed method is tested in a simple simulation scenario.
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）
Carnegie Mellon University（卡内基梅隆大学）；Bosch Research Pittsburgh（博世匹兹堡研究院）；NVIDIA（英伟达）；AICrowd；Amazon（亚马逊）；Arrival Ltd.（Arrival公司）；Pinterest
We present the results of our autonomous racing virtual challenge, based on the newly-released Learn-to-Race (L2R) simulation framework, which seeks to encourage interdisciplinary research in autonomous driving and to help advance the state of the art on a realistic benchmark. Analogous to racing being used to test cutting-edge vehicles, we envision autonomous racing to serve as a particularly challenging proving ground for autonomous agents as: (i) they need to make sub-second, safety-critical decisions in a complex, fast-changing environment; and (ii) both perception and control must be robu…
University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）；RWTH Aachen University（亚琛工业大学）
In many robotic tasks, such as autonomous drone racing, the goal is to travel through a set of waypoints as fast as possible. A key challenge for this task is planning the time-optimal trajectory, which is typically solved by assuming perfect knowledge of the waypoints to pass in advance. The resulting solution is either highly specialized for a single-track layout, or suboptimal due to simplifying assumptions about the platform dynamics. In this work, a new approach to near-time-optimal trajectory generation for quadrotors is presented. Leveraging deep reinforcement learning and relative gate…
In head-to-head racing, an accurate model of interactive behavior of the opposing target vehicle (TV) is required to perform tightly constrained, but highly rewarding maneuvers such as overtaking. However, such information is not typically made available in competitive scenarios, we therefore propose to construct a prediction and uncertainty model given data of the TV from previous races. In particular, a one-step Gaussian process (GP) model is trained on closed-loop interaction data to learn the behavior of a TV driven by an unknown policy. Predictions of the nominal trajectory and associated…
University of Sannio（萨尼奥大学）；Czech Technical University in Prague（捷克布拉格技术大学）；Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）
A Nonlinear Model Predictive Control (NMPC) strategy aimed at controlling a small-scale car model for autonomous racing competitions is presented in this paper. The proposed control strategy is concerned with minimizing the lap time while keeping the vehicle within track boundaries. The optimization problem considers both the vehicle's actuation limits and the lateral and longitudinal forces acting on the car modeled through the Pacejka's magic formula and a simple drivetrain model. Furthermore, the approach allows to safely race on a track populated by static obstacles generating collision-fr…
University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）；Intel（英特尔）
Dynamically changing environments, unreliable state estimation, and operation under severe resource constraints are fundamental challenges that limit the deployment of small autonomous drones. We address these challenges in the context of autonomous, vision-based drone racing in dynamic environments. A racing drone must traverse a track with possibly moving gates at high speed. We enable this functionality by combining the performance of a state-of-the-art planning and control system with the perceptual awareness of a convolutional neural network (CNN). The resulting modular system is both pla…
In this paper, we study a long-term planning scenario that is based on drone racing competitions held in real life. We conducted this experiment on a framework created for "Game of Drones: Drone Racing Competition" at NeurIPS 2019. The racing environment was created using Microsoft's AirSim Drone Racing Lab. A reinforcement learning agent, a simulated quadrotor in our case, has trained with the Policy Proximal Optimization(PPO) algorithm was able to successfully compete against another simulated quadrotor that was running a classical path planning algorithm. Agent observations consist of data …
A Hybrid Sampling-Based Trajectory Planner with Game-Theoretic Guidance for Autonomous Racing
Professorship of Autonomous Vehicle Systems, TUM School of Engineering and Design, Technical University of Munich（慕尼黑工业大学工程与设计学院自动驾驶车辆系统教授组）；Munich Institute of Robotics and Machine Intelligence (MIRMI)（慕尼黑机器人与机器智能研究所）
Sony Europe B.V., Schlieren/Switzerland Branch（索尼欧洲有限公司，施利伦/瑞士分公司）；University of Zurich（苏黎世大学）
Autonomous car racing is a major challenge in robotics. It raises fundamental problems for classical approaches such as planning minimum-time trajectories under uncertain dynamics and controlling the car at the limits of its handling. Besides, the requirement of minimizing the lap time, which is a sparse objective, and the difficulty of collecting training data from human experts have also hindered researchers from directly applying learning-based approaches to solve the problem. In the present work, we propose a learning-based system for autonomous car racing by leveraging a high-fidelity phy…
The rising popularity of driver-less cars has led to the research and development in the field of autonomous racing, and overtaking in autonomous racing is a challenging task. Vehicles have to detect and operate at the limits of dynamic handling and decisions in the car have to be made at high speeds and high acceleration. One of the most crucial parts in autonomous racing is path planning and decision making for an overtaking maneuver with a dynamic opponent vehicle. In this paper we present the evaluation of a track based offline policy learning approach for autonomous racing. We define spec…
One of the main challenges in autonomous racing is to design algorithms for motion planning at high speed, and across complex racing courses. End-to-end trajectory synthesis has been previously proposed where the trajectory for the ego vehicle is computed based on camera images from the racecar. This is done in a supervised learning setting using behavioral cloning techniques. In this paper, we address the limitations of behavioral cloning methods for trajectory synthesis by introducing Differential Bayesian Filtering (DBF), which uses probabilistic Bézier curves as a basis for inferring optim…
Centre for Automation and Robotic Engineering Science, The University of Auckland, New Zealand（自动化与机器人工程科学中心，奥克兰大学，新西兰）；New Dexterity research group, The University of Auckland, New Zealand（新灵活性研究组，奥克兰大学，新西兰）
While autonomous racing performance in Time-Trial scenarios has seen significant progress and development, autonomous wheel-to-wheel racing and overtaking are still severely limited. These limitations are particularly apparent in real-life driving scenarios where state-of-the-art algorithms struggle to safely or reliably complete overtaking manoeuvres. This is important, as reliable navigation around other vehicles is vital for safe autonomous wheel-to-wheel racing. The F1Tenth Competition provides a useful opportunity for developing wheel-to-wheel racing algorithms on a standardised physical …
Diponegoro University（迪波内戈罗大学）；Bandung Institute of Technology（万隆理工学院）
This paper presents one approach in designing a Fire Fighting Robot which has been contested annually in a robotic student competition in many countries following the rules initiated at the Trinity College. The approach makes use of computer simulation and animation in a virtual reality environment. In the simulation, the amount of time, starting from home until the flame is destroyed, can be confirmed. The efficacy of algorithms and parameter values employed can be easily evaluated. Rather than spending time building the real robot in a trial and error fashion, now students can explore more v…
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）
Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing
Autonomous Robots and Vehicles Laboratory, College of Engineering, Virginia Commonwealth University（弗吉尼亚联邦大学工程学院自主机器人与车辆实验室）；Department of Mechanical Engineering, Virginia Tech（弗吉尼亚理工学院机械工程系）；Robotics Department, University of Michigan（密歇根大学机器人系）
Microsoft（微软）；Stanford University（斯坦福大学）；University of Zurich and ETH（苏黎世大学和苏黎世联邦理工学院）
Autonomous drone racing is a challenging research problem at the intersection of computer vision, planning, state estimation, and control. We introduce AirSim Drone Racing Lab, a simulation framework for enabling fast prototyping of algorithms for autonomy and enabling machine learning research in this domain, with the goal of reducing the time, money, and risks associated with field robotics. Our framework enables generation of racing tracks in multiple photo-realistic environments, orchestration of drone races, comes with a suite of gate assets, allows for multiple sensor modalities (monocul…
A Sim-to-Real Deep Learning-based Framework for Autonomous Nano-drone Racing
University of Bologna（博洛尼亚大学）；Dalle Molle Institute for Artificial Intelligence, USI-SUPSI（USI-SUPSI 达勒·莫勒人工智能研究所）；Autonomous Robotics Research Center, Technology Innovation Institute（技术创新研究院自主机器人研究中心）；ETH Zürich（苏黎世联邦理工学院）
Drone racing is becoming a popular e-sport all over the world, and beating the best human drone race pilots has quickly become a new major challenge for artificial intelligence and robotics. In this paper, we propose a strategy for autonomous drone racing which is computationally more efficient than navigation methods like visual inertial odometry and simultaneous localization and mapping. This fast light-weight vision-based navigation algorithm estimates the position of the drone by fusing race gate detections with model dynamics predictions. Theoretical analysis and simulation results show t…
