Existing Advanced Driver Assistance Systems primarily focus on the vehicle directly ahead, often overlooking potential risks from following vehicles. This oversight can lead to ineffective handling of high risk situations, such as high speed, closely spaced, multi vehicle scenarios where emergency braking by one vehicle might trigger a pile up collision. To overcome these limitations, this study introduces a novel deep reinforcement learning based algorithm for longitudinal control and collision avoidance. This proposed algorithm effectively considers the behavior of both leading and following vehicles. Its implementation in simulated high risk scenarios, which involve emergency braking in dense traffic where traditional systems typically fail, has demonstrated the algorithm ability to prevent potential pile up collisions, including those involving heavy duty vehicles.
Avoidance of an unexpected obstacle without reinforcement learning: Why not using advanced control-theoretic tools?
CRAN (CNRS, UMR 7039)), Université de Lorraine（CRAN（CNRS，UMR 7039），法国洛林大学）；LIX (CNRS, UMR 7161), École polytechnique（LIX（CNRS，UMR 7161），巴黎高等师范学院）；LJLL (CNRS, UMR 7598), Sorbonne Université（LJLL（CNRS，UMR 7598），索邦大学）；AL.I.E.N., 7 rue Maurice Barrès, 54330 Vézelise, France（AL.I.E.N., 法国韦泽利斯）
Aircraft collision avoidance systems have long been a key factor in keeping our airspace safe. Over the past decade, the FAA has supported the development of a new family of collision avoidance systems called the Airborne Collision Avoidance System X (ACAS X), which model the collision avoidance problem as a Markov decision process (MDP). Variants of ACAS X have been created for both manned (ACAS Xa) and unmanned aircraft (ACAS Xu and ACAS sXu). The variants primarily differ in the types of collision avoidance maneuvers they issue. For example, ACAS Xa issues vertical collision avoidance advis…
School of Mechanical and Aerospace Engineering,Nanyang Technological University, Singapore, 637460（机械与航空航天工程学院，南洋理工大学，新加坡）；School of Transportation Science and Engineering, Beihang University, Beijing, China, 100191（交通运输科学与工程学院，北航大学，北京）
Technical University of Munich（慕尼黑工业大学）；EURECOM（欧洲通信学院）
Reliable pedestrian crash avoidance mitigation (PCAM) systems are crucial components of safe autonomous vehicles (AVs). The nature of the vehicle-pedestrian interaction where decisions of one agent directly affect the other agent's optimal behavior, and vice versa, is a challenging yet often neglected aspect of such systems. We address this issue by modeling a Markov decision process (MDP) for a simulated AV-pedestrian interaction at an unmarked crosswalk. The AV's PCAM decision policy is learned through deep reinforcement learning (DRL). Since modeling pedestrians realistically is challenging…
The primary goal of this paper is to examine the motorcyclists' activities during the overtaking period, as well as to develop a model of total overtaking time. For the experimental study, instrumented motorcycles were used to collect data and design an overall overtaking period model. The possibility of death during an attempt to overtake is maximum for people walking on rural roads, mainly identified by a scarcity of pathways and higher speeds of vehicles. It is important to recognize and prototype driver actions during the overtaking moves to set up collision avoidance strategies in order t…
EROAS: 3D Efficient Reactive Obstacle Avoidance System for Autonomous Underwater Vehicles using 2.5D Forward-Looking Sonar
Department of Aerospace Eng.（航空航天工程系）；Indian Institute of Science（印度科学研究所）；Department of Electrical and Electronics Eng.（电子与电气工程系）；Birla Institute of Technology and Science（比拉理工学院）；Department of Computer Science and Eng.（计算机科学与工程系）；Shiv Nadar University（施瓦纳大学）
The Allstate Corporation（好事达公司）；Stanford University（斯坦福大学）
Many automotive applications, such as Advanced Driver Assistance Systems (ADAS) for collision avoidance and warnings, require estimating the future automotive risk of a driving scene. We present a low-cost system that predicts the collision risk over an intermediate time horizon from a monocular video source, such as a dashboard-mounted camera. The modular system includes components for object detection, object tracking, and state estimation. We introduce solutions to the object tracking and distance estimation problems. Advanced approaches to the other tasks are used to produce real-time pred…
Tsinghua University（清华大学）；University of Michigan（密歇根大学）
Safeguard functions such as those provided by advanced emergency braking (AEB) can provide another layer of safety for autonomous vehicles (AV). A smart safeguard function should adapt the activation conditions to the driving policy, to avoid unnecessary interventions as well as improve vehicle safety. This paper proposes a driving-policy adaptive safeguard (DPAS) design, including a collision avoidance strategy and an activation function. The collision avoidance strategy is designed in a reinforcement learning framework, obtained by Monte-Carlo Tree Search (MCTS). It can learn from past colli…
As passenger vehicle technologies have advanced, so have their capabilities to avoid obstacles, especially with developments in tires, suspensions, steering, as well as safety technologies like ABS, ESC, and more recently, ADAS systems. However, environments around passenger vehicles have also become more complex, and dangerous. There have previously been studies that outline driver tendencies and performance capabilities when attempting to avoid obstacles while driving passenger vehicles. Now that autonomous vehicles are being developed with obstacle avoidance capabilities, it is important to…
Tod’Aérs - Transparent Organization for Aeronautics and Space Research（Tod'Aérs - 航空航天研究透明组织）；Space Generation Advisory Council（太空世代咨询委员会）；Moscow Aviation Institute（莫斯科航空学院）；Univerité Sultan Moulay Slimane（苏丹穆莱·斯利曼大学）
This paper introduced the space mission DikpolaSat Mission, how this research fits into the mission, and the importance of having a trained DNN model instead of the usual GN&C functionality. This paper shows how the controller demonstration is carried out by having the spacecraft follow a desired path, specified in the referenced model. Increases can be made by examining the route used to construct a DNN and understanding the effects of various activating functions on system efficiency. The obstacle avoidance algorithm is built into the control features to respond spontaneously using inputs fr…
Graz University of Technology（格拉茨技术大学）；MAGNA Steyr Fahrzeugtechnik AG & CO KG（麦格纳斯太尔汽车技术股份两合公司）
Virtual development and prototyping has already become an integral part in the field of automated driving systems (ADS). There are plenty of software tools that are used for the virtual development of ADS. One such tool is CarMaker from IPG Automotive, which is widely used in the scientific community and in the automotive industry. It offers a broad spectrum of implementation and modelling possibilities of the vehicle, driver behavior, control, sensors, and environmental models. Focusing on the virtual development of highly automated driving functions on the vehicle guidance level, it is essen…
CReSTIC, IUT de Troyes（特鲁瓦大学技术学院CReSTIC实验室）；Mines ParisTech, PSL Research University（巴黎高等矿业学院，PSL研究大学）；École polytechnique（巴黎综合理工学院）；AL.I.E.N.（AL.I.E.N.公司）；IFSTTAR（法国法国交通发展与网络科学研究院）；CNRS（法国国家科学研究中心）；Supélec（高等电力学院）；Université Paris-Sud（巴黎第十一大学）
A new model-free setting and the corresponding "intelligent" P and PD controllers are employed for the longitudinal and lateral motions of a vehicle. This new approach has been developed and used in order to ensure simultaneously a best profile tracking for the longitudinal and lateral behaviors. The longitudinal speed and the derivative of the lateral deviation, on one hand, the driving/braking torque and the steering angle, on the other hand, are respectively the output and the input variables. Let us emphasize that a "good" mathematical modeling, which is quite difficult, if not impossible …
Deep learning methods have revolutionized mobile robotics, from advanced perception models for an enhanced situational awareness to novel control approaches through reinforcement learning. This paper explores the potential of federated learning for distributed systems of mobile robots enabling collaboration on the Internet of Robotic Things. To demonstrate the effectiveness of such an approach, we deploy wheeled robots in different indoor environments. We analyze the performance of a federated learning approach and compare it to a traditional centralized training process with a priori aggregat…
Dalian University of Technology（大连理工大学）；University of Southern California（南加州大学）
Intelligence agents and multi-agent systems play important roles in scenes like the control system of grouped drones, and multi-agent navigation and obstacle avoidance which is the foundational function of advanced application has great importance. In multi-agent navigation and obstacle avoidance tasks, the decision-making interactions and dynamic changes of agents are difficult for traditional route planning algorithms or reinforcement learning algorithms with the increased complexity of the environment. The classical multi-agent reinforcement learning algorithm, Multi-agent deep deterministi…
AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
School of Software Engineering, XJTU（软件工程学院，西安交通大学）；Horizon Robotics；Shenzhen Loop Area Institute（深圳河套学院）；University of Chinese Academy of Sciences（中国科学院大学）
本文提出一种 cascaded 框架，通过将纵向规划转化为路径条件推理过程，提升自动驾驶的协调性和安全性。方法引入锚点回归设计和规划导向的数据增强策略，实现在 Bench2Drive 上达到 SOTA 性能。
This paper addresses the shared lateral control for both lane-keeping and obstacle avoidance tasks of a driver steering assist system (DSAS). In this work, we propose a novel approach to deal with the interactions between the human (driver) and the machine (DSAS) by introducing into the vehicle system a fictive nonlinear term representing the driver activity. In this way, the actions of the DSAS are computed according to the driver behaviors (actions and intentions). Based on Takagi-Sugeno control technique together with Lyapunov stability tools, the designed controller is able to handle a lar…
Increasingly sophisticated function development is taking place with the aim of developing efficient, safe and increasingly Automated Driving Functions. This development is possible with the use of diverse data from sources such as Navigation Systems, eHorizon, on-board sensor data, Vehicle-to-Infrastructure (V2I) and Vehicle-to-Vehicle (V2V) communication. Increasing challenges arise with the dependency on large amounts of real-time data coming from off-board sources. At the core of addressing these challenges lies the concept of a Digital Dependability Identity (DDI) of a component or system…
Learning Machines is developing a flexible, cross-industry, advanced analytics platform, targeted during stealth-stage at a limited number of specific vertical applications. In this paper, we aim to integrate a general machine system to learn a variant of tasks from simulation to real world. In such a machine system, it involves real-time robot vision, sensor fusion, and learning algorithms (reinforcement learning). To this end, we demonstrate the general machine system on three fundamental tasks including obstacle avoidance, foraging, and predator-prey robot. The proposed solutions are implem…
Vehicle-pedestrian interaction (VPI) is one of the most challenging tasks for automated driving systems. The design of driving strategies for such systems usually starts with verifying VPI in simulation. This work proposed an improved framework for the study of VPI in uncontrolled pedestrian crossing scenarios. The framework admits the mutual effect between the pedestrian and the vehicle. A multi-state social force based pedestrian motion model was designed to describe the microscopic motion of the pedestrian crossing behavior. The pedestrian model considers major interaction factors such as t…
