Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Autonomous and Human-Driven Vehicles Interacting in a Roundabout: A Quantitative and Qualitative Evaluation

Laura Ferrarotti, Massimiliano Luca, Gabriele Santin, Giorgio Previati, Gianpiero Mastinu, Massimiliano Gobbi, Elena Campi, Lorenzo Uccello, Antonino Albanese, Praveen Zalaya, Alessandro Roccasalva, Bruno Lepri

TL;DR

An end-to-end framework is proposed to study mixed-autonomy traffic in a Milan roundabout by integrating SUMO, VI-WorldSim, and a cockpit, with RL-based AV control trained via PPO to minimize crossing time $T$ and emissions $E$. The framework supports both quantitative metrics (time, emissions, fuel consumption) and qualitative measures (safety and smoothness perceptions) through human-in-the-loop evaluation. Results show that higher AV penetration reduces crossing times and pollution for both AVs and HVs, and participants perceive safer and smoother traffic at higher AV shares. The work contributes a practical methodology for evaluating AV policies in hybrid traffic and highlights the societal benefits and acceptance considerations of AV integration.

Abstract

Optimizing traffic dynamics in an evolving transportation landscape is crucial, particularly in scenarios where autonomous vehicles (AVs) with varying levels of autonomy coexist with human-driven cars. While optimizing Reinforcement Learning (RL) policies for such scenarios is becoming more and more common, little has been said about realistic evaluations of such trained policies. This paper presents an evaluation of the effects of AVs penetration among human drivers in a roundabout scenario, considering both quantitative and qualitative aspects. In particular, we learn a policy to minimize traffic jams (i.e., minimize the time to cross the scenario) and to minimize pollution in a roundabout in Milan, Italy. Through empirical analysis, we demonstrate that the presence of AVs} can reduce time and pollution levels. Furthermore, we qualitatively evaluate the learned policy using a cutting-edge cockpit to assess its performance in near-real-world conditions. To gauge the practicality and acceptability of the policy, we conduct evaluations with human participants using the simulator, focusing on a range of metrics like traffic smoothness and safety perception. In general, our findings show that human-driven vehicles benefit from optimizing AVs dynamics. Also, participants in the study highlight that the scenario with 80% AVs is perceived as safer than the scenario with 20%. The same result is obtained for traffic smoothness perception.

Autonomous and Human-Driven Vehicles Interacting in a Roundabout: A Quantitative and Qualitative Evaluation

TL;DR

An end-to-end framework is proposed to study mixed-autonomy traffic in a Milan roundabout by integrating SUMO, VI-WorldSim, and a cockpit, with RL-based AV control trained via PPO to minimize crossing time and emissions . The framework supports both quantitative metrics (time, emissions, fuel consumption) and qualitative measures (safety and smoothness perceptions) through human-in-the-loop evaluation. Results show that higher AV penetration reduces crossing times and pollution for both AVs and HVs, and participants perceive safer and smoother traffic at higher AV shares. The work contributes a practical methodology for evaluating AV policies in hybrid traffic and highlights the societal benefits and acceptance considerations of AV integration.

Abstract

Optimizing traffic dynamics in an evolving transportation landscape is crucial, particularly in scenarios where autonomous vehicles (AVs) with varying levels of autonomy coexist with human-driven cars. While optimizing Reinforcement Learning (RL) policies for such scenarios is becoming more and more common, little has been said about realistic evaluations of such trained policies. This paper presents an evaluation of the effects of AVs penetration among human drivers in a roundabout scenario, considering both quantitative and qualitative aspects. In particular, we learn a policy to minimize traffic jams (i.e., minimize the time to cross the scenario) and to minimize pollution in a roundabout in Milan, Italy. Through empirical analysis, we demonstrate that the presence of AVs} can reduce time and pollution levels. Furthermore, we qualitatively evaluate the learned policy using a cutting-edge cockpit to assess its performance in near-real-world conditions. To gauge the practicality and acceptability of the policy, we conduct evaluations with human participants using the simulator, focusing on a range of metrics like traffic smoothness and safety perception. In general, our findings show that human-driven vehicles benefit from optimizing AVs dynamics. Also, participants in the study highlight that the scenario with 80% AVs is perceived as safer than the scenario with 20%. The same result is obtained for traffic smoothness perception.
Paper Structure (18 sections, 12 equations, 3 figures, 7 tables)

This paper contains 18 sections, 12 equations, 3 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Simulations in SUMO
  4. VI-WorldSim
  5. VI-Worldsim and SUMO Interaction
  6. The Cockpit
  7. Reinforcement Learning
  8. Literature Review
  9. AVs-HVs Interaction
  10. RL design for AVs
  11. Methodology
  12. Turning SUMO into a realistic Reinforcement Learning-based environment
  13. Proximal Policy Optimization
  14. Roundabout Design and Data Collection
  15. Results and Discussion
  16. ...and 3 more sections

Figures (3)

  • Figure 1: A) The cockpit was installed at DrisMi Laboratory of the Polytechnic University of Milan. B) An example of the output of VI-WorldSim after the integration with SUMO.
  • Figure 2: A) The selected roundabout in Milan observed from OpenStreetMap; and in B), the corresponding design of the roundabout in SUMO. Also, realistic traffic loads for fine-tuning have been measured through field measurements.
  • Figure 3: Concerning the quantitative analysis, we measured the impact of AV penetration rate on emissions, fuel consumption and average time to cross the scenario. On the left, we have the results related to emissions. In the middle, we show the results for fuel consumption while on the right we have the average crossing time. As we can observe, the best results are obtained for the scenario with 100% of AVs. However, having some AVs (e.g., 10% to 90% penetration rate already provides some benefits. Interestingly enough, also HV benefits from the penetration rate of AVs.