Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cooperative Decision-Making in Shared Spaces: Making Urban Traffic Safer through Human-Machine Cooperation

Balint Varga, Dongxu Yang, Sören Hohmann

TL;DR

This work tackles safe interactions between automated vehicles and vulnerable road users in shared urban spaces by introducing cooperative decision-making with an explicit pedestrian prediction model. It extends a general cooperative/shared control framework to mixed-traffic scenarios and develops an explicit pedestrian Model Predictive Controller that predicts pedestrian futures using a sigmoid-based velocity model and time-to-collision metrics. Compared against rule-based and implicit-pedestrian MPC baselines, the proposed approach yields superior safety-efficiency trade-offs and real-time feasibility in simulations, with deadlock prevention through intention-aware adjustments. The results suggest practical potential for real-world deployment, highlighting the importance of explicit pedestrian modeling and cooperative negotiation for trust-building and safety in low-speed urban driving. Future work plans real-vehicle experiments and human-in-the-loop studies to validate robustness in diverse, realistic conditions.

Abstract

In this paper, a cooperative decision-making is presented, which is suitable for intention-aware automated vehicle functions. With an increasing number of highly automated and autonomous vehicles on public roads, trust is a very important issue regarding their acceptance in our society. The most challenging scenarios arise at low driving speeds of these highly automated and autonomous vehicles, where interactions with vulnerable road users likely occur. Such interactions must be addressed by the automation of the vehicle. The novelties of this paper are the adaptation of a general cooperative and shared control framework to this novel use case and the application of an explicit prediction model of the pedestrian. An extensive comparison with state-of-the-art algorithms is provided in a simplified test environment. The results show the superiority of the proposed model-based algorithm compared to state-of-the-art solutions and its suitability for real-world applications due to its real-time capability.

Cooperative Decision-Making in Shared Spaces: Making Urban Traffic Safer through Human-Machine Cooperation

TL;DR

This work tackles safe interactions between automated vehicles and vulnerable road users in shared urban spaces by introducing cooperative decision-making with an explicit pedestrian prediction model. It extends a general cooperative/shared control framework to mixed-traffic scenarios and develops an explicit pedestrian Model Predictive Controller that predicts pedestrian futures using a sigmoid-based velocity model and time-to-collision metrics. Compared against rule-based and implicit-pedestrian MPC baselines, the proposed approach yields superior safety-efficiency trade-offs and real-time feasibility in simulations, with deadlock prevention through intention-aware adjustments. The results suggest practical potential for real-world deployment, highlighting the importance of explicit pedestrian modeling and cooperative negotiation for trust-building and safety in low-speed urban driving. Future work plans real-vehicle experiments and human-in-the-loop studies to validate robustness in diverse, realistic conditions.

Abstract

In this paper, a cooperative decision-making is presented, which is suitable for intention-aware automated vehicle functions. With an increasing number of highly automated and autonomous vehicles on public roads, trust is a very important issue regarding their acceptance in our society. The most challenging scenarios arise at low driving speeds of these highly automated and autonomous vehicles, where interactions with vulnerable road users likely occur. Such interactions must be addressed by the automation of the vehicle. The novelties of this paper are the adaptation of a general cooperative and shared control framework to this novel use case and the application of an explicit prediction model of the pedestrian. An extensive comparison with state-of-the-art algorithms is provided in a simplified test environment. The results show the superiority of the proposed model-based algorithm compared to state-of-the-art solutions and its suitability for real-world applications due to its real-time capability.
Paper Structure (17 sections, 15 equations, 4 figures, 3 tables)

This paper contains 17 sections, 15 equations, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. State of the Art
  3. Rule-based Controllers
  4. Model-based Controllers
  5. Model Predictive Control
  6. Game theory
  7. Cooperative and Shared Control Concepts
  8. Shortcomings of the Solutions from the Literature
  9. Cooperative Decision-Making for Shared Space Problems
  10. Explicit Pedestrian Model Predictive Controller
  11. Intention Lowering for Deadlock Prevention
  12. Adaptation of the Cooperative Control Framework
  13. Simulation Comparison with state-of-the-art Solutions
  14. Model Predictive Controller with the State-of-the-Art Implicit Pedestrian
  15. Setup of the Analysis
  16. ...and 2 more sections

Figures (4)

  • Figure 1: An example scenario, in which an interaction between the pedestrian and the automated vehicle happens. With courtesy of version1 GmbH.
  • Figure 2: The top-down perspective of the automated vehicle-pedestrian interaction in a shared space
  • Figure 3: Shared control framework of pedestrian-automated vehicle interaction, adapted from Flemisch et. al2019_JoiningBluntPointy_flemisch
  • Figure 4: Simulation results of the scenario with decision of a test person is illustrated, in which the pedestrian crosses before the vehicle.