Top

Open Access 2024 | Open Access | Book

Cooperatively Interacting Vehicles

Methods and Effects of Automated Cooperation in Traffic

Editors: Christoph Stiller, Matthias Althoff, Christoph Burger, Barbara Deml, Lutz Eckstein, Frank Flemisch

Publisher: Springer International Publishing

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Table of Contents

About this book

This open access book explores the recent developments automated driving and Car2x-communications are opening up attractive opportunities future mobility. The DFG priority program “Cooperatively Interacting Automobiles” has focused on the scientific foundations for communication-based automated cooperativity in traffic.

Communication among traffic participants allows for safe and convenient traffic that will emerge in swarm like flow. This book investigates requirements for a cooperative transport system, motion generation that is safe and effective and yields social acceptance by all road users, as well as appropriate system architectures and robust cooperative cognition.

For many years, traffic will not be fully automated, but automated vehicles share their space with manually driven vehicles, two-wheelers, pedestrians, and others. Such a mixed traffic scenario exhibits numerous facets of potential cooperation. Automated vehicles must understand basic principles of human interaction in traffic situations. Methods for the anticipation of human movement as well as methods for generating behavior that can be anticipated by others are required. Explicit maneuver coordination among automated vehicles using Car2X-communications allows generation of safe trajectories within milliseconds, even in safety-critical situations, in which drivers are unable to communicate and react, whereas today's vehicles delete their information after passing through a situation, cooperatively interacting automobiles should aggregate their knowledge in a collective data and information base and make it available to subsequent traffic.

Frontmatter

PDF

Perception and Prediction with Implicit Communication

Frontmatter

Open Access

How Cyclists’ Body Posture Can Support a Cooperative Interaction in Automated Driving

Abstract

Automated driving is continuously evolving and will be integrated more and more into urban traffic in the future. Since urban traffic is characterized by a high number of space-sharing conflicts, the issue of an appropriate interaction with other road users, especially with pedestrians and cyclists, becomes increasingly important. This chapter provides an overview of the research project “KIRa” (Cooperative Interaction with Cyclists in automated Driving), which investigated the interaction between automated vehicles and cyclists according to four project aims. First, the investigation of body posture as a predictor of the cyclists’ starting process. Second, the development of a VR cycling simulation and validation in terms of perceived criticality and experience of presence. Third, the experimental evaluation of a drift-diffusion model for vehicle deceleration detection. And fourth, the investigation of factors affecting cyclists’ gap acceptance. With these research aims, it was the project’s intention to contribute to a better understanding of the cyclists’ perception of communication signals and to improve the ability of automated vehicles to predict cyclists’ intentions. The results can provide an important contribution to the cooperative design of the interaction between automated vehicles and cyclists.

Daniel Trommler, Claudia Ackermann, Dominik Raeck, Josef F. Krems

PDF View full text

Open Access

Prediction of Cyclists’ Interaction-Aware Trajectory for Cooperative Automated Vehicles

Abstract

Cooperative behaviour is one of the most crucial factors for safety and comfort in shared traffic spaces. While a human driver might be able to automatically identify behavioural indicators of other traffic participants to predict their movement, an automated vehicle is not. This is especially important in interaction situations with vulnerable road users (VRU), such as cyclists. The focus of this work is to implement, evaluate and compare different possible methods of trajectory forecasts for cyclists in order to estimate their behavioural intention. With accurate trajectory information of the VRU, an automated vehicle might be able to plan a cooperative reaction ahead in time and guarantee a comfortable traffic flow. In sum, three different neural network architectures have been tested with the main focus on a CNN, which is capable of incorporating map data into the trajectory forecast. The results showed, that including external influencing factors, like the infrastructure of a traffic scene, can have a beneficial effect on the accuracy of the cyclist’s predicted movement.

Dominik Raeck, Timo Pech, Daniel Trommler, Klaus Mößner

PDF View full text

Open Access

Detecting Intentions of Vulnerable Road Users Based on Collective Intelligence as a Basis for Automated Driving

Abstract

The project Detecting Intentions of Vulnerable Road Users Based on Collective Intelligence as a Basis for Automated Driving (DeCoInt\(^2\)) focuses on detecting the intentions of vulnerable road users (VRUs) in automated driving using cooperative technologies. Especially in urban areas, VRUs, e.g., pedestrians and cyclists, will continue to play an essential role in mixed traffic. For an accident-free and highly efficient traffic flow with automated vehicles, it is vital to perceive VRUs and their intentions and analyze them similarly to humans when driving and forecasting VRU trajectories. Doing this reliably and robustly with a multimodal sensor system (e.g., cameras, LiDARs, accelerometers, and gyroscopes in mobile devices) in real-time is a big challenge. We follow a holistic, cooperative approach to recognize humans’ movements and forecast their trajectories. Heterogeneous open sets of agents, i.e., collaboratively interacting vehicles, infrastructure, and VRUs equipped with mobile devices, exchange information to determine individual models of their surrounding environment, allowing an accurate and reliable forecast of VRU basic movements and trajectories. The collective intelligence of cooperating agents resolves occlusions, implausibilities, and inconsistencies. We developed new methods by considering and combining novel signal processing and modeling techniques with machine learning-based pattern recognition approaches. The cooperation between agents happens on several levels: the VRU perception level, the level of recognized trajectories, or the level of already detected intentions.

Stefan Zernetsch, Viktor Kress, Maarten Bieshaar, Jan Schneegans, Günther Reitberger, Erich Fuchs, Bernhard Sick, Konrad Doll

PDF View full text

Open Access

Analysis and Simulation of Driving Behavior at Inner City Intersections

Abstract

Inner city intersections are a challenging scenario for human drivers as well as for the development of autonomous vehicles. This is especially the case for unsignalized intersections where the right before left rule applies. At these intersections, ambiguous situations can arise. In this chapter, we cover two aspects of this intersection type: First, we use driving data from a field study conducted in inner city traffic to analyze the relationship between intersections and human driving behavior. For that, we describe the intersection, its surrounding environment and the traffic there by features that constitute an intersection’s complexity (e.g. street width, visibility conditions, number of cooperation vehicles). With those we are able to predict features describing the driving behavior reliably. Second, we propose a decision making algorithm for unsignalized inner city T-junctions. The algorithm is modeled as a discrete event system and does not rely on any explicit communication. Instead, only the observable state is used. This includes the map, the positions and velocities of the cooperation vehicles and the driving pattern. We introduce the algorithm in detail and present results of a comprehensive simulation for validation. The algorithm is able to drive through all situations in the simulation safely.

Hannes Weinreuter, Nadine-Rebecca Strelau, Barbara Deml, Michael Heizmann

PDF View full text

Perception and Prediction with Explicit Communication

Frontmatter

Open Access

Robust Local and Cooperative Perception Under Varying Environmental Conditions

Abstract

Robust perception of the environment under a variety of ambient conditions is crucial for autonomous driving. Convolutional Neural Networks (CNNs) achieve high accuracy for vision-based object detection, but are strongly affected by adverse weather conditions such as rain, snow, and fog, as well as soiled sensors. We propose physically correct simulations of these conditions for vision-based systems, since publicly available data sets lack scenarios with different environmental conditions. In addition, we provide a data set of real images containing adverse weather for evaluation. By training CNNs with augmented data, we achieve a significant improvement in robustness for object detection. Furthermore, we present the advantages of cooperative perception to compensate for limited sensor ranges of local perception. A key aspect of autonomous driving is safety; therefore, a robustness evaluation of the perception system is necessary, which requires an appropriate safety metric. In contrast to existing approaches, our safety metric focuses on scene semantics and the relevance of surrounding objects. The performance of our approaches is evaluated using real-world data as well as augmented and virtual reality scenarios.

Jörg Gamerdinger, Georg Volk, Sven Teufel, Alexander von Bernuth, Stefan Müller, Dennis Hospach, Oliver Bringmann

PDF View full text

Open Access

Design and Evaluation of V2X Communication Protocols for Cooperatively Interacting Automobiles

Abstract

This chapter studies two key communication services for the support of cooperative driving capabilities using Vehicle-to-Everything (V2X) communications: sensor data sharing and maneuver coordination. Based on the current state of the art in research and pre-standardization of V2X communications, we enhance the protocol design for both services and assess their performance by discrete-event simulations in highway and city scenarios. The first part of this chapter addresses the performance improvement of sensor data sharing by two complementary strategies. The shared sensor data are adapted to the available resources on the used channel. Furthermore, the redundancy of the transmitted information is reduced to lower the load on the wireless channel, whereas several approaches are proposed and assessed. The second part of the chapter analyzes cooperative maneuver coordination protocols. We propose a distributed approach based on the explicit exchange of V2X messages, which introduces priorities in maneuver coordination and studies several communication patterns for the negotiation and coordination of maneuvers among two and more vehicles. The results demonstrate the potential of V2X communications for automated driving, showcase several approaches for enhancements of sensor data sharing and maneuver coordination, and indicate the performance of these enhancements.

Quentin Delooz, Daniel Maksimovski, Andreas Festag, Christian Facchi

PDF View full text

Motion Planning

Frontmatter

Open Access

Interaction-Aware Motion Planning as a Game

Abstract

Motion planning for automated vehicles (AVs) in mixed traffic, where AVs share the road with human-driven vehicles, is a challenging task. To reduce the complexity, state-of-the-art planning approaches often assume that the future motion of surrounding vehicles can be predicted independently of the AV’s plan. This separation can lead to suboptimal, overly conservative behavior especially in highly interactive traffic situations. In this work, we introduce a motion planning algorithm to generate interaction-aware behavior for highly interactive scenarios. The presented algorithm is based upon a reformulation of a bi-level optimization problem, which frames interactions between a human driver and a AV as a Stackelberg game. In contrast to existing works, the algorithm can account for general nonlinear state and input constraints. Further, we introduce mechanisms to integrate cooperation and courtesy into motion planning to prevent overly aggressive driving behavior.

Christoph Burger, Shengchao Yan, Wolfram Burgard, Christoph Stiller

PDF View full text

Open Access

Designing Maneuver Automata of Motion Primitives for Optimal Cooperative Trajectory Planning

Abstract

Trajectory planning techniques form a central step to enable autonomous driving. The motion primitives method generates an automaton of precomputed maneuvers with structure-exploiting properties. Thereby, the trajectory planning problem can be reduced to finding an admissible/optimal sequence of motion primitives. In this chapter, we present ways to designing maneuver automata based on different system models and on either analytical or data-based approaches for automaton generation. Moreover, numerical methods for computing optimal maneuvers are listed and we discuss graph-based planning techniques. A subsequent chapter shows the evaluation of motion primitives automata in the Cyber-Physical Mobility Lab.

Matheus V. A. Pedrosa, Patrick Scheffe, Bassam Alrifaee, Kathrin Flaßkamp

PDF View full text

Open Access

Prioritized Trajectory Planning for Networked Vehicles Using Motion Primitives

Abstract

The computation time required to solve nonconvex, nonlinear optimization problems increases rapidly with their size. This poses a challenge in trajectory planning for multiple networked vehicles with collision avoidance. In the centralized formulation, the optimization problem size increases with the number of vehicles in the networked control system (NCS), rendering the formulation unusable for experiments. We investigate two methods to decrease the complexity of networked trajectory planning. First, we approximate the optimization problem by discretizing the vehicle dynamics with an automaton, which turns it into a graph-search problem. Our search-based trajectory planning algorithm has a limited horizon to further decrease computation complexity. We achieve recursive feasibility by design of the automaton which models the vehicle dynamics. Second, we distribute the optimization problem to the vehicles with prioritized distributed model predictive control (P-DMPC), which reduces the problem size. To counter the incompleteness of P-DMPC, we propose a framework for time-variant priority assignment. The framework expands recursive feasibility to every vehicle in the NCS. We present two time-variant priority assignment algorithms for road vehicles, one to improve vehicle progress and one to improve computation time of the NCS. We evaluate our approach for online trajectory planning of multiple networked vehicles in simulations and experiments.

Patrick Scheffe, Matheus V. A. Pedrosa, Kathrin Flaßkamp, Bassam Alrifaee

PDF View full text

Open Access

Maneuver-Level Cooperation of Automated Vehicles

Abstract

Cooperative behavior of automated vehicles at the maneuver level is of utmost importance for the efficient and safe use of traffic space. This chapter discusses a vehicle-to-vehicle communication-based negotiation and cooperation method for maneuver cooperation. The method is based on the negotiation about explicitly defined reservation areas on the road for the exclusive use of a particular traffic participant. It covers all standard traffic situations occurring on regular streets and thus achieves universal applicability. The evaluation of simulations and driving tests shows the suitability of the method for effective maneuver cooperation in various traffic situations. Furthermore, based on this method, the planning and execution of cooperative maneuvers in emergency situations are investigated. Simulations show that collisions can be avoided in relevant cases by this method. Moreover, further simulations and driving tests show that joint maneuvers can avoid sharp braking maneuvers in many situations. In addition, research on a methodology for implicit maneuver cooperation is presented. Based on reinforcement learning methods, partially cooperative decision-making functions are studied in a setting that benefits from cooperative behavior. The evaluation shows that cooperative behaviors of road participants can be achieved using this technique.

Matthias Nichting, Daniel Heß, Frank Köster

PDF View full text

Open Access

Hierarchical Motion Planning for Consistent and Safe Decisions in Cooperative Autonomous Driving

Abstract

The immersion of autonomous cars in continuously changing environments of on-road traffic requires procedures for decision-making with fast adaptation as well as guarantees on safe motion and collision-avoidance. This contribution proposes a three-layer hierarchic decomposition of the task of automatically steering the autonomous car along a designated route in cooperation with neighbored vehicles. The upper layer of the hierarchy identifies cooperative groups of those vehicles which are involved in a joint scenario for a phase of the planning horizon. The medium layer employs set-based computations of the free space for any vehicle of a joint scenario together with constrained optimal control to determine optimized motion plans. These plans are used on the lower layer as reference signals for tracking control in order to realize motion trajectories. The architecture ensures consistency of the vehicle motion with respect to safety for given assumptions, as well as relatively small computation times by combining offline with online computation.

Jan Eilbrecht, Olaf Stursberg

PDF View full text

Open Access

Specification-Compliant Motion Planning of Cooperative Vehicles Using Reachable Sets

Abstract

Automated vehicles must comply explicitly with specifications, including traffic-based and handcrafted rules, in order for them to safely and effectively participate in mixed traffic. In addition to driving individually, there are many traffic situations in which cooperation between vehicles maximizes their collective benefits, including preventing collisions. To realize these benefits, we compute specification-compliant reachable sets for vehicles, i.e., sets of states which can be reached by vehicles over time that are constrained by a set of considered specifications. We summarize and combine our previous works on computing specification-compliant reachable sets and negotiating conflicting reachable sets within a group of cooperating vehicles. As a result, conflicts between specification-compliant reachable sets of vehicles are resolved, and specification-compliant trajectories can be individually planned for each vehicle within the negotiated reachable sets using arbitrary motion planners.

Edmond Irani Liu, Matthias Althoff

PDF View full text

Open Access

AutoKnigge—Modeling, Evaluation and Verification of Cooperative Interacting Automobiles

Abstract

The development of cooperative driving functions to optimize traffic systems shows high potential to improve individual autonomous driving systems with respect to topics like traffic flow, vehicle safety and user comfort. The core concept of the presented solutions is the Local Traffic System (LTS). Following the messages defined in European Telecommunications Standards Institute (ETSI) Intelligent Transport Systems (ITS) G5 for Vehicle-to-everything (V2X) cooperation we introduce concepts and implementations to intelligently group vehicles based on the exchanged V2X data with respect to the individual vehicle capability for cooperation. Based on the determined grouping, we present algorithms for cooperative trajectory planning. We develop a verification method for the cooperatively planned trajectories within a LTS. The verification guarantees collision avoidance and deadlock-freeness in real-time. Finally we introduce a model language based on MontiArc to enable a systematic representation and description of the presented concepts for grouping, cooperation and interaction.

Christian Kehl, Maximilian Kloock, Evgeny Kusmenko, Lutz Eckstein, Bassam Alrifaee, Stefan Kowalewski, Bernhard Rumpe

PDF View full text

Open Access

Implicit Cooperative Trajectory Planning with Learned Rewards Under Uncertainty

Abstract

Urban traffic scenarios often require high interaction between traffic participants to ensure safety and efficiency. While the capabilities of automated driving systems have made remarkable progress in the past decade, they lack two critical abilities: anticipation and provision of cooperation between traffic participants without communication, i.e., implicit cooperation. Observing the behavior of other traffic participants, humans infer the need to cooperate and act accordingly. Our work presents a system that utilizes a sampling-based cooperative trajectory planner that accounts for all possible actions of other traffic participants, enabling cooperation. Further, we extend the planner employing learned reward models based on expert trajectories to demonstrate its ability to adapt to a desired human driving style for smooth integration into today’s traffic. Lastly, we address the issue of measurement uncertainties to robustify the decision-making process in real-world environments utilizing return distributions over start states according to a belief. We exemplify the effectiveness of our solutions on 15 challenging multi-agent scenarios.

Karl Kurzer, Philipp Stegmaier, Nikolai Polley, J. Marius Zöllner

PDF View full text

Open Access

Learning Cooperative Trajectories at Intersections in Mixed Traffic

Abstract

Intersections are a significant bottleneck in traffic and have been a topic of much research. Optimization approaches incorporating traffic models are often limited by the intractable complexity resulting from the combinatorial explosion associated with increasing numbers of vehicles. Learning cooperative maneuver policies with deep neural networks from traffic data is a promising approach to address this issue. This chapter presents two approaches for managing traffic at intersections using deep reinforcement learning. The first approach learns an adaptive traffic signal controller, serving as a trajectory planner for all vehicles at the intersection. For smaller intersections with less traffic and fewer lanes, traffic signs are preferred over traffic lights due to their lower cost and higher efficiency. The second approach uses a centralized control unit to optimize efficiency and equity by ordering automated vehicles to yield to vehicles on conflicting routes with lower priorities. Self-driving cars have the potential to improve traffic flow in mixed environments with human-driven vehicles. The chapter evaluates the approaches using a traffic simulator with simulated and real-world traffic data. The approaches achieve state-of-the-art performance in terms of traffic efficiency and equity compared to non-learning and other learning-based methods. The chapter concludes with a discussion of possible future work on learning cooperative trajectories in mixed traffic.

Shengchao Yan, Tim Welschehold, Daniel Büscher, Christoph Burger, Christoph Stiller, Wolfram Burgard

PDF View full text

Human Factors

Frontmatter

Open Access

Cooperative Hub for Cooperative Research on Cooperatively Interacting Vehicles: Use Cases, Design and Interaction Patterns

Abstract

This chapter describes central cooperative activities in the research priority program Cooperatively Interacting Vehicles (CoInCar). If the whole research program CoInCar can be seen as a wheel, which is turning research questions into answers, knowledge and hopefully progress for society, the individual research projects described in the other chapters could be seen as spokes of the wheel, and the aspects described in this chapter as an informal cooperative hub of the wheel. Starting with common essential definitions, a use case catalogue was derived and documented. Based on that, cooperation and interaction pattern were sketched and documented into a pattern database. While the details of the research hub described here are specific for this DFG priority program, the general principles of a research hub could be transferred to any other research and development activity.

Frank Flemisch, Nicolas Herzberger, Marcel Usai, Marcel Baltzer, Maximilian Schwalm, Gudrun Voß, Josef Krems, Laura Quante, Daniel Trommler, Nadine Strelau, Christoph Burger, Christoph Stiller

PDF View full text

Open Access

Cooperation Between Vehicle and Driver: Predicting the Driver’s Takeover Capability in Cooperative Automated Driving Based on Orientation Patterns

Abstract

This chapter first describes central development steps of cooperative vehicle control before focusing on the cooperation within the vehicle, between driver and co-system. To enable smooth transitions within this internal cooperation, both agents (driver and co-system) need a mutual understanding of the current capabilities for safely executing the driving task. For this purpose, first the model of confidence horizons is briefly introduced, which represents these mutual capability assessments. In the following, the focus of this chapter is on the assessment of the driver’s ability to take over. First, the state of the art of Driver State Monitoring Systems (DSMS) as well as current challenges are presented. Here it is shown that a prediction based purely on driver observation is not yet possible. Therefore, an alternative approach, the diagnostic takeover request (TOR), is presented, which predicts the takeover capability based on the driver’s initial orientation reaction. In the following, two driving simulator studies are presented in which the diagnostic TOR was used for the first time and thereafter the results are presented and discussed. Finally, a brief outlook is given on how both the diagnostic TOR and the concept of confidence horizons will be further developed.

Nicolas Herzberger, Marcel Usai, Maximilian Schwalm, Frank Flemisch

PDF View full text

Open Access

Confidence Horizons: Dynamic Balance of Human and Automation Control Ability in Cooperative Automated Driving

Abstract

This chapter presents the concept of confidence horizon for cooperative vehicles. The confidence horizon is designed to let the automation predict its own and the human’s abilities to control the vehicle in the near future. Based on the pattern approach originating from Alexander et al. [1], the confidence horizon concept is instantiated with a pattern framework. In case of a necessary takeover of the driving task by the human, a mode transition pattern is initiated. In order to determine when the takeover is required, which pattern to start and when to omit the takeover attempt and directly start a minimum risk maneuver, the confidence horizon for both human and co-system is an important parameter. A visual representation of the confidence horizon for the driver in different scenarios prior to a takeover request was explored. Intermediate results of a simulator study are presented, which assess the confidence horizon in automation safety-critical takeover scenarios involving an intersection and a broken-down vehicle on a highway.

Marcel Usai, Nicolas Herzberger, Yang Yu, Frank Flemisch

PDF View full text

Open Access

Cooperation Behavior of Drivers at Inner City Deadlock-Situations

Abstract

In urban traffic, there are several situations in which the right of way is not regulated. For automated vehicles in mixed traffic to show behavior that is considered acceptable by all parties, the cooperation behavior of drivers in these situations must be understood. An observational study identified several behaviors in these situations at equal narrow passages and T-intersections that can be classified as offensive and defensive. These behaviors were tested in an experiment whether they can communicate the intention to drive or to stop. Drivers respond to defensive behaviors of the cooperation partner by continuing to drive, and stopping when the behavior is offensive. In the equal narrow passage, drivers felt safest when they drove first, whereas at the T-intersection, drivers felt safest when the cooperation partner drove first. In further experiments, it was shown that at T-intersections the entry position has an influence on whether drivers drive first or stop. Pedestrians or other traffic do not have an influence on the behavior. However, if drivers follow a vehicle that is driving ahead of them, they drive first through the deadlock situation. Recommendations for the behavior of automated vehicles in these situations are derived from the findings of the studies.

Nadine-Rebecca Strelau, Jonas Imbsweiler, Gloria Pöhler, Hannes Weinreuter, Michael Heizmann, Barbara Deml

PDF View full text

Open Access

Measuring and Describing Cooperation Between Road Users—Results from CoMove

Abstract

Safe and efficient traffic requires that road users interact and cooperate with each other. Especially in situations which are not explicitly regulated, and the right of way is not clearly defined, it is of great importance that road users are able to communicate their own intentions and understand the communication and cooperation behaviour of the other involved road users. When automated vehicles enter the current traffic system, their ability to fit into the system, that is their ability to communicate and cooperate, will determine their success. Therefore, the development of cooperatively interacting, automated vehicles requires detailed knowledge about human cooperation behaviour in traffic, which can only be obtained using appropriate methods and measures. By focusing on road narrowings and lane changing, this chapter gives an overview on how to measure cooperation between road users, considering methods for data collection, subjective and objective measures of cooperation as well as behaviour modeling, to support the systematic research on cooperation in road traffic. This overview is extended by findings from studies conducted within CoInCar, including results on factors influencing human behaviour in cooperative situations, either in a manual or an automated setting, and initial findings from modeling the cognitive processes underlying cooperative driving behaviour.

Laura Quante, Tanja Stoll, Martin Baumann, Andor Diera, Noèmi Földes-Cappellotto, Meike Jipp, Caroline Schießl

PDF View full text

Title: Cooperatively Interacting Vehicles
Editors: Christoph Stiller
Matthias Althoff
Christoph Burger
Barbara Deml
Lutz Eckstein
Frank Flemisch
Publisher: Springer International Publishing
Electronic ISBN: 978-3-031-60494-2
Print ISBN: 978-3-031-60493-5
DOI: https://doi.org/10.1007/978-3-031-60494-2