Grid platooning by swarm intelligence
Financed by Continental Automotive Romania, Period: 11.2018-12.2018
Vehicle platooning became an interesting topic in the last years, many researchers and practitioners from the academia and industry trying to develop new theories and design appropriate control methods and communication methodologies in order to bring this concept as fast as possible on the roads. Since vehicles drive on multi-lane roads and highways, the subsequent paradigm was to treat vehicles as swarms, i.e., groups of vehicles that travel closely together on different lanes and are electronically connected.
Platooning brings advantages such as reduction of fuel consumption, increasing the safety and comfort of traveling, and increasing capacity of roads.
The scope is to develop a swarm intelligence (distributed functions) framework to platooning:
Swarm intelligence:
To reach the final goal, the development of multiple-lane grid platooning based on swarm intelligence, there are a few steps to follow:
Note that, all of these are done to increase the road space utilization, to control optimally the traffic flow, to reduce the fuel consumption and to increase the safety.
Work Package 1 (WP1): Platooning grounds
Task 1.1. Existing approaches acquaintance – theory survey
Task 1.2. Grid platooning initial simulations based on existing algorithms
Task 1.3. Requirements definition for individual vehicles in the grid platoon
Deliverable 1: Matlab simulator for grid platooning
Deliverable 2: Report with the survey result and the requirements for grid platooning
Work Package 2 (WP2): Swarm robotics theory
Task 2.1. Existing approaches acquaintance – theory survey
Task 2.2. Comparative analysis of the existing algorithms for grid platooning purposes
Deliverable 3: Algorithm with the chosen method for swarm-based grid platooning
Deliverable 4: Report with the survey result and the comparative analysis of the algorithms
Work Package 3 (WP3): Coupled vehicle and network simulators
Task 3.1. Identification of simulators for networked vehicles
Task 3.2. Functional analysis of the simulators for networked vehicles
Task 3.3. Comparative analysis of the existing simulators for networked vehicles
Deliverable 5: Demonstration of the simulation capabilities of each simulator
Deliverable 6: Report with the functional and comparative analysis of the simulators
Work Package 4 (WP4): Swarm path planning
Task 4.1. Comparative analysis of the existing swarm optimization approaches for grid platooning purposes
Deliverable 7: Path planning algorithm suitable for grid platooning
Deliverable 8: Report with the comparative analysis for swarm optimization
Work Package 5 (WP5): System integration
Task 5.1. System architecture definition using the requirements from WP1
Task 5.2. Integrate the algorithms from WP2 and WP4 in the simulator from WP3
Deliverable 9: Full system demonstrator for one use case
Deliverable 10: Report with the system architecture description and the full system demonstrator
Caruntu C.F., C.M. Pascal, L. Ferariu, and C.R. Comsa, Trajectory optimization through connected cooperative control for multiple-vehicle flocking, 28th Mediterranean Conference on Control and Automation, Saint-Raphael, France, pp. 915-920, 2020. (ISI proceedings)
https://ieeexplore.ieee.org/document/9182964
Caruntu C.F., C.M. Pascal, A. Maxim, and O. Pauca, Bio-inspired coordination and control of autonomous vehicles in future manufacturing and goods transportation, 21st IFAC World Congress, Berlin, Germany, IFAC-PapersOnLine, 53(2), pp. 10861-10866, 2020.
https://www.sciencedirect.com/science/article/pii/S2405896320335771
Caruntu C.F., L. Ferariu, C.M. Pascal, N. Cleju, and C.R. Comsa, Connected cooperative control for multiple-lane automated vehicle flocking on highway scenarios, 23rd International Conference on System Theory, Control and Computing, Sinaia, Romania, pp. 791-796, 2019. (ISI proceedings)
https://ieeexplore.ieee.org/document/8885496
Caruntu C.F., L. Ferariu, C.M. Pascal, N. Cleju, and C.R. Comsa, A concept of multiple-lane vehicle grouping by swarm intelligence, 24th IEEE Conference on Emerging Technologies and Factory Automation, Zaragoza, Spain, pp. 1183-1188, 2019. (ISI proceedings)
https://ieeexplore.ieee.org/document/8868955
Caruntu C.F., R.C. Rafaila, and A. Maxim, Multiple-lane vehicle platooning based on a multi-agent distributed model predictive control strategy, 22nd International Conference on System Theory, Control and Computing, Sinaia, Romania, pp. 759-765, 2018. (ISI proceedings)
Our solution is based on creating the ability of passenger cars to coordinate their driving behavior when passing through intelligent intersections equipped with smart infrastructure.
Let’s improve safety and efficiency by developing collaborative traffic functions in
smart intersections!
