Jovin D'SA
Research Subjects
Research Interests
Jovin D'SA has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
Sangjae Bae
Honda Research Institute USA, Inc., San Jose, CA, USA
3 shared publications- David Isele
Honda Research Institute, San Jose, CA, USA
2 shared publications - Donggun Lee
Department of Mechanical and Aerospace Engineering, North Carolina State University, Raleigh, USA
2 shared publications - Faizan M. Tariq
Honda Research Institute, San Jose, CA, USA
2 shared publications - Gabriel Chenevert
North Carolina State University
2 shared publications - Xinlei Zhang
Magnetic Medical Robotics Lab, Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, China
2 shared publications
Latest Publications
- Open Access
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (3) , 3724-3731
Differentiable Weights-Varying Nonlinear MPC via Gradient-Based Policy Learning: An Autonomous Vehicle Guidance Example
Tuning Model Predictive Control (MPC) cost weights for multiple, competing objectives is labor-intensive. Derivative-free automated methods, such as Bayesian Optimization, reduce manual effort but remain slow, while Differentiable MPC (Diff-MPC) exploits solver sensitivities for faster gradient-based tuning. However, existing Diff-MPC approaches learn a single global weight set, which may be suboptimal as operating conditions change. Conversely, black-box Reinforcement Learning Weights-Varying MPC (RL-WMPC) requires long training times and a lot of data. In this work, we introduce gradient-based policy learning for Differentiable Weights-Varying MPC (Diff-WMPC). By backpropagating solver-in-the-loop sensitivities through a lightweight policy that maps look-ahead observations to MPC weights, our Diff-WMPC yields rapid, sample-efficient adaptation at runtime. Extensive simulation on a full-scale racecar model demonstrates that Diff-WMPC outperforms state-of-the-art static-weight baselines and is competitive with weights-varying algorithms, while reducing training time from over an hour to under two minutes relative to RL-WMPC. The learned policy transfers zero-shot to unseen conditions and, with quick online fine-tuning, reaches environment-specific performance.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (3) , 3724-3731
Open AccessDifferentiable Weights-Varying Nonlinear MPC via Gradient-Based Policy Learning: An Autonomous Vehicle Guidance Example
Tuning Model Predictive Control (MPC) cost weights for multiple, competing objectives is labor-intensive. Derivative-free automated methods, such as Bayesian Optimization, reduce manual effort but remain slow, while Differentiable MPC (Diff-MPC) exploits solver sensitivities for faster gradient-based tuning. However, existing Diff-MPC approaches learn a single global weight set, which may be suboptimal as operating conditions change. Conversely, black-box Reinforcement Learning Weights-Varying MPC (RL-WMPC) requires long training times and a lot of data. In this work, we introduce gradient-based policy learning for Differentiable Weights-Varying MPC (Diff-WMPC). By backpropagating solver-in-the-loop sensitivities through a lightweight policy that maps look-ahead observations to MPC weights, our Diff-WMPC yields rapid, sample-efficient adaptation at runtime. Extensive simulation on a full-scale racecar model demonstrates that Diff-WMPC outperforms state-of-the-art static-weight baselines and is competitive with weights-varying algorithms, while reducing training time from over an hour to under two minutes relative to RL-WMPC. The learned policy transfers zero-shot to unseen conditions and, with quick online fine-tuning, reaches environment-specific performance.
- Open Access
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (12) , 12437-12444
ZSG-MPPI: Robust Model-Predictive Path-Integral Method for Disturbance Handling
Zero-sum games (ZSGs) provide a robust control framework for autonomous systems operating underdisturbances. However, existing methods often face challenges in achieving real-time computation and maintaining high performance in unseen environments. Recent sampling-based approaches alleviate some of these issues but remain computationally inefficient, limiting robustness under real-time constraints. To address this, we propose ZSG-MPPI, a real-time robust control algorithm built on the Model-Predictive Path-Integral (MPPI) framework. By establishing a connection between ZSGs and optimal control problems (OCPs), our method leverages sampling-efficient MPPI techniques for OCPs while analytically computing the control policy for ZSGs. Simulation and hardware experiments demonstrate that our ZSG-MPPI achieves real-time performance and outperforms baselines in both robustness and sampling efficiency.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (12) , 12437-12444
Open AccessZSG-MPPI: Robust Model-Predictive Path-Integral Method for Disturbance Handling
Zero-sum games (ZSGs) provide a robust control framework for autonomous systems operating underdisturbances. However, existing methods often face challenges in achieving real-time computation and maintaining high performance in unseen environments. Recent sampling-based approaches alleviate some of these issues but remain computationally inefficient, limiting robustness under real-time constraints. To address this, we propose ZSG-MPPI, a real-time robust control algorithm built on the Model-Predictive Path-Integral (MPPI) framework. By establishing a connection between ZSGs and optimal control problems (OCPs), our method leverages sampling-efficient MPPI techniques for OCPs while analytically computing the control policy for ZSGs. Simulation and hardware experiments demonstrate that our ZSG-MPPI achieves real-time performance and outperforms baselines in both robustness and sampling efficiency.