Publications & Outreach
Publications on Koopman Operator Theory
Outreach Activities
IDETC 2024
🎯 𝗛𝗶𝗴𝗵𝗹𝗶𝗴𝗵𝘁𝘀:
𝗙𝘂𝗻𝗱𝗮𝗺𝗲𝗻𝘁𝗮𝗹𝘀: State-of-the-art methods in perception, planning and control, with applied machine learning for autonomous driving.
𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵: Emerging topics with assorted examples in data-driven modeling and control including behavioral cloning, reinforcement learning, Koopman operator theory, etc.
MECC 2024 (F1tenth workshop)
🎯 𝗛𝗶𝗴𝗵𝗹𝗶𝗴𝗵𝘁𝘀:
𝗙𝘂𝗻𝗱𝗮𝗺𝗲𝗻𝘁𝗮𝗹𝘀: State-of-the-art methods in perception, planning and control, with applied machine learning for autonomous driving.
𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵: Emerging topics with assorted examples in data-driven modeling and control including behavioral cloning, reinforcement learning, Koopman operator theory, etc.
MECC 2024
CHALLENGES AND OPPORTUNITIES FOR MODELING, IDENTIFICATION, AND CONTROL OF OFF-ROAD VEHICLE AUTONOMY
In recent years, UGVs have expanded across diverse applications, facing challenges in modeling and control due to non-linear wheel-terrain interactions and environmental perturbations. This talk introduces the Multi-Model Parameterized Koopman (MMPK) framework, a state-of-the-art data-driven solution for adaptable UGV control under uncertain conditions. With real-time terrain adaptability and a unified offline modeling and online control loop, MMPK offers superior path-tracking performance in both on-road and off-road environments.
All Publications
The following is a comprehensive list of my scientific contributions during my PhD, encompassing advancements in perception, motion planning, modeling, and controls within end-to-end and hybrid physics-aware learning-based frameworks.
1. Joglekar, Ajinkya & Vaidya, Umesh & Krovi, Venkat. (2024). Modeling and Control of Off-road Autonomous Vehicles with Situationally Aware Data-Driven Framework. 10.13140/RG.2.2.13288.48642. (under review)
2. Mehta, Dhruv & Joglekar, Ajinkya & Krovi, Venkat. (2024). Deep Reinforcement Learning for Coordinated Payload Transport in Biped-Wheeled Robots. 10.13140/RG.2.2.10251.71207/1. (under review)
3. Samak, C. V., Samak, T. V., Joglekar, A., Vaidya, U., & Krovi, V. (2024). Digital Twins Meet the Koopman Operator: Data-Driven Learning for Robust Autonomy. arXiv preprint arXiv:2409.10347. (under review)
4. Joglekar, Ajinkya & Samak, Chinmay & Samak, Tanmay & Krovi, Venkat & Vaidya, Umesh. (2024). Expanding Autonomous Ground Vehicle Navigation Capabilities through a Multi-Model Parameterized Koopman Framework. 10.13140/RG.2.2.33007.24485. (under review)
5. Krovi, Venkat & Joglekar, Ajinkya & Samak, Chinmay & Samak, Tanmay & Ranganathan, Shyam & Sathe, Sumedh. (2024). Data Driven Vehicle Dynamics System Identification Using Gaussian Processes. 10.4271/2024-01-2022.
6. Sutavani, S., Zheng, A., Joglekar, A., Smereka, J., Gorsich, D., Krovi, V., & Vaidya, U. (2023). ARTIFICIAL NEURAL NETWORK BASED TERRAIN RECONSTRUCTION FOR OFF-ROAD AUTONOMOUS VEHICLES USING LIDAR.
7. Joglekar, A., Samak, C., Samak, T., Kosaraju, K. C., Smereka, J., Brudnak, M., ... & Vaidya, U. (2023). Analytical Construction of Koopman EDMD Candidate Functions for Optimal Control of Ackermann-Steered Vehicles. IFAC-PapersOnLine, 56(3), 619-624.
8. A. Joglekar et al., "Data-Driven Modeling and Experimental Validation of Autonomous Vehicles Using Koopman Operator," 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, MI, USA, 2023, pp. 9442-9447, doi: 10.1109/IROS55552.2023.10341797.
9. Joglekar, A., Sathe, S., Misurati, N., Srinivasan, S., Schmid, M. J., & Krovi, V. (2022). Deep Reinforcement Learning Based Adaptation of Pure-Pursuit Path-Tracking Control for Skid-Steered Vehicles. IFAC-PapersOnLine, 55(37), 400-407.
10. A. Joglekar, V. Krovi, M. Brudnak and J. M. Smereka, "Hybrid Reinforcement Learning based controller for autonomous navigation," 2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring), Helsinki, Finland, 2022, pp. 1-6, doi: 10.1109/VTC2022-Spring54318.2022.9861014.
11. Joglekar, A., Deshpande, B., Basuthakur, M., and Krovi, V., "Fusing Offline and Online Trajectory Optimization Techniques for Goal-to-Goal Navigation of a Scaled Autonomous Vehicle," SAE Technical Paper 2021-01-0097, 2021, https://doi.org/10.4271/2021-