Brief Research Summary

Vehicle Coordination at Intersections

The coordination of autonomous vehicles approaching an intersection has recently attracted increasing research interest. The main motivation behind this research topic is to use automation in order to (a) reduce the amount of accidents, (b) reduce pollution and energy consumption and (c) increase the capacity of the infrastructure.
In order to achieve these three goals, it is necessary to introduce communication between the involved agents and the infrastructure, and to design a suitable algorithmic framework in order to compute a solution. The coordination problem can be framed as a distributed mixed-integer optimal control problem. While this class of problems has a high complexity and is known to be NP-hard, by designing tailored optimisation algorithms and heuristics one can aim at computing at least approximated solutions in a rather short time. We have introduced one of the steps towards such an algorithm: we assume a prescribed crossing order is given and focus on the continuous part of the problem, i.e. the solution of the distributed optimal control problem. By exploiting the structure of the problem and by designing tailored optimisation algorithms we (a) minimise the amount of information to be communicated and (b) greatly reduce the computational burden. Experimental results demonstrated real-time feasibility, robustness and precision of our algorithm.

Below you can see a frame extracted from one of the videos of our experiments. The three vehicles are trying to track a constant speed of 50 km/h and, without coordination, would reach the intersection at the same time. For safety reasons, we first tested the algorithm first in a three-parallel-lanes configuration, with the intersection marked by two white lines.

frame1
First two vehicles crossing with the third one behind and a central coordinator in a car standing still.
frame2
Last two vehicles crossing.

After out test campaign successfully demonstrated the reliability of the control algorithm, we tested it in a real crossing scenario and recorded the video below.

Video of three vehicles crossing at 50 km/h.

Autonomous Driving in Urban Environments

Urban environments pose severe challenges for autonomous driving, since the presence of non-autonomous, non-cooperative agents, e.g., pedestrians, cyclists and human-driven vehicles, makes it hard to provide strict safety guarantees. In this project, we work both on pedestrian modeling and on robust MPC formulations with safety guarantees. The main challenge in this case is given by the fact that, unlike in standard robust MPC, the uncertainty is uncontrollable. This requires an ad-hoc formulation in order to guarantee safety at all times and recursive feasibility.

Video of safe autonomous driving in urban environments. Scenario with two pedestrians: the vehicle has to yield to the first one, but can safely cross before the second one. Simulations first and experiments on a real vehicle next. The black empty box shows the car at the end of the prediction horizon: in order to guarantee safety, the vehicle predicts to always stop. However, it only does so when strictly necessary. All details can be found in the papers cited at the bottom of this webpage.

Publications

Journal:

  1. I. Batkovic, M. Ali, P. Falcone and M. Zanon. Safe Trajectory Tracking in Uncertain Environments. IEEE Transactions on Automatic Control, 2023 (in press)
  2. R. Hult, M. Zanon, S. Gros, and P. Falcone. A Semi-Distributed Interior Point Algorithm for Optimal Coordination of Automated Vehicles at Intersections. IEEE Transactions on Control Systems Technology, 2022
  3. I. Batkovic, U. Rosolia, M. Zanon, and P. Falcone. A Robust Scenario MPC Approach for Uncertain Multi-modal Obstacles. IEEE Control System Letters, 2021
  4. R. Hult, M. Zanon, S. Gros, H. Wymeersch and P. Falcone. Optimization-based Coordination of Connected, Automated Vehicles at Intersections. Vehicle System Dynamics, 2020
  5. R. Hult, M. Zanon, G. Frison, S. Gros and P. Falcone. Experimental Validation of a Semi-Distributed SQP Method for Optimal Coordination of Automated vehicles at Intersections. Optimal Control Applications and Methods, 2020
  6. R. Hult, M. Zanon, S. Gros, and P. Falcone. Optimal Coordination of Automated Vehicles at Intersections: Theory and Experiments. IEEE Transactions on Control Systems Technology, 2019

Conference:

  1. R. Hult, M. Zanon, S. Gros and P. Falcone. Optimal Coordination of Automated Vehicles at Intersections with Turns. Proceedings of the European Control Conference (ECC), 2019
  2. I. Batkovic, M. Zanon, M. Ali and P. Falcone. Real-Time Constrained Trajectory Planning and Vehicle Control for Proactive Autonomous Driving with Road Users. Proceedings of the European Control Conference (ECC), 2019
  3. R. Hult, M. Zanon, S. Gros and P. Falcone. An MIQP-based heuristic for Optimal Coordination of Vehicles at Intersections. Proceedings of the Conference on Decision and Control (CDC), 2018
  4. M. Zanon, R. Hult, S. Gros and P. Falcone. Experimental Validation of Distributed Optimal Vehicle Coordination. Proceedings of the European Control Conference (ECC), 2018
  5. R. Hult, M. Zanon, S. Gros and P. Falcone. Energy-Optimal Coordination of Autonomous Vehicles at Intersections. Proceedings of the European Control Conference (ECC), 2018
  6. I. Batkovic, M. Zanon, N. Lubbe and P. Falcone. A Computationally Efficient Model for Pedestrian Motion Prediction. Proceedings of the European Control Conference (ECC), 2018
  7. J. Shi, Y. Zheng, Y. Jiang, M. Zanon, R. Hult, B. Houska. Distributed control algorithm for vehicle coordination at traffic intersections. Proceedings of the European Control Conference (ECC), 2018
  8. M. Zanon, S. Gros, P. Falcone and H. Wymeersch. An Asynchronous Algorithm for Optimal Vehicle Coordination at Traffic Intersections. Proceedings of the World Congress of the International Federation of Automatic Control, 2017
  9. Y. Jiang, M. Zanon, R. Hult and B. Houska. A Distributed Algorithm for Optimal Vehicle Coordination at Traffic Intersecitons. Proceedings of the World Congress of the International Federation of Automatic Control, 2017
  10. R. Hult, M. Zanon, S. Gros and P. Falcone. Primal Decomposition of the Optimal Coordination of Vehicles at Traffic Intersections. Proceedings of the Conference on Decision and Control (CDC), 2016
  11. R. Verschueren, M. Zanon, R. Quirynen and M. Diehl. Time-optimal Race Car Driving using an Online Exact Hessian based Nonlinear MPC Algorithm. Proceedings of the European Control Conference (ECC), 2016
  12. R. Verschueren, S. De Bruyne, M. Zanon, J. V. Frasch and M. Diehl. Towards Time-Optimal Race Car Driving Using Nonlinear MPC in Real Time. Proceedings of the Conference on Decision and Control (CDC), 2014
  13. J. V. Frasch, A. Gray, M. Zanon, H. J. Ferreau, S. Sager, F. Borrelli and M. Diehl. An Auto-generated Nonlinear MPC Algorithm for Real-Time Obstacle Avoidance of Ground Vehicles. Proceedings of the European Control Conference (ECC), 2013
  14. M. Zanon, J. V. Frasch and M. Diehl. Nonlinear Moving Horizon Estimation for Combined State and Friction Coefficient Estimation in Autonomous Driving.Proceedings of the European Control Conference (ECC), 2013
Advertisement