Novel Data-Driven Algorithms for Autonomous Vehicle Path Planning Problems with Uncertain Data Parameters

Project began in 2019 and was completed in 2022 Q1.

During the exploratory phase and first year of the project, the focus was to develop offline high-level planning algorithms for a team of ground vehicles while considering system and environment uncertainties, leader-follower pattern with unmanned ground vehicles (UGVs) following the manned leader. The current phase of the project focuses on two stages following the planning stage, and are as follows: evaluation stage – the data on vehicle casualties, time spent on point of interests (POIs), and travel time are continuously collected from the field, and the feasibility and quality of the solution obtained from planning stage is continuously monitored; and execution stage – obtain quick recourse actions for the teams whenever the current solution loses feasibility or deteriorates in quality or a new ad-hoc task gets added. For example, a convoying mission will employ manned ground vehicles and UGVs in a leader-follower pattern with several UGVs following the single manned leader. Beyond the offline plans, if some of the assets are compromised or fail in a hostile attack or more time is required at certain POIs or if any a new POI is added then what are the quick recourse solutions that will help ensure the team can complete the mission?

This project focuses on the following fundamental question that arises during the evaluation and execution stages of deploying a team of GVs: How to estimate the sensitivity of the solutions obtained during offline planning, and what are the quick recourse (online) solutions in the event of deviations in the resources availability and environments?

Publications:

• V. S. Chirala, K. Sundar, S. Venkatachalam, J. M. Smereka and S. Kassoumeh, “Heuristics for Multi-Vehicle Routing Problem Considering Human-Robot Interactions,” in IEEE Transactions on Intelligent Vehicles, vol. 8, no. 5, pp. 3228-3238, May 2023, doi: 10.1109/TIV.2023.3261274.
• Chirala, V. S., Venkatachalam, S., Smereka, J. M., and Kassoumeh, S. (January 31, 2022). “A Multi-Objective Optimization Approach for Multi-Vehicle Path Planning Problems Considering Human–Robot Interactions.” ASME. J. Auton. Veh. Sys. October 2021; 1(4): 041002. https://doi.org/10.1115/1.4053426
• Fazeli S. S., Venkatachalam S., Smereka J. M., “Efficient algorithms for autonomous electric vehicles’ min-max routing problem,” IEEE Transactions on Intelligent Transportation Systems. [JIF:6.319, OPSEC- 4492 ] (under review). https://doi.org/10.48550/arXiv.2008.03333
• Chirala, V.S., Venkatachalam, S. & Smereka, J.M. UV Mission Planning Under Uncertainty in Vehicles’ Availability. J Intell Robot Syst 108, 26 (2023). https://doi.org/10.1007/s10846-023-01860-z https://doi.org/10.48550/arXiv.2010.06112
• Venkatachalam S., Bansal M., Smereka M.J., Lee J., “Two-stage stochastic programming approach for path planning problems under travel time and availability uncertainties,” https://arxiv.org/abs/1910.04251
• Venkatachalam S., Bansal M., Smereka J. M., “Stochastic Programming Model for Unmanned Ground Vehicles” GVSETS, Autonomous Ground Systems Technical Session, August 13-15, 2019, Novi, MI. (PDF)

#1.30 #1.A60