Home / Faculties / Sweksha Jain

Sweksha Jain

Quick facts

Sweksha has a strong academic and research background in Systems and Control Engineering, with a Ph.D. from Centre for Systems and Control, IIT Bombay. Her expertise includes swarm robotics, decentralized control, autonomous navigation, and multi-robot coordination in communication-denied and GPS-denied environments. Her research focuses on perception-driven control strategies, swarm self-clustering, swarm navigation and switched system stability analysis. Her teaching interests include control systems, robotics, embedded systems, machine learning, and autonomous systems, integrating theoretical foundations with practical engineering applications.

Publications

No publications added yet.

Research

No Research Interests added yet.

Sweksha Jain

Assistant Professor

Sweksha Jain is an Assistant Professor in the Department of Mechanical and Aerospace Engineering at Mahindra University. She holds a Ph.D. in Systems and Control Engineering from the Indian Institute of Technology Bombay (IIT Bombay), an M.Tech in Process Control from the National Institute of Technology Warangal, and a bachelor’s degree in Electronics and Instrumentation from Samrat Ashok Technological Institute (SATI), Vidisha. Her interdisciplinary academic background integrates electronics, instrumentation, process control, and systems engineering, complemented by specialized research expertise in robotics. Her research focuses on swarm robotics, decentralized control, autonomous navigation, multi-robot coordination, and stability analysis of switched dynamical systems. She develops perception-driven, communication-free control frameworks that enable robotic swarms to achieve collective behaviours, including self-clustering and safe-area navigation, using onboard sensing without relying on global positioning systems or inter-robot communication. Her technical expertise includes control theory, LiDAR-based perception, ROS, Gazebo-based robotic simulation, potential-field navigation, and optimization-based control strategies. Her teaching interests include control systems, robotics, embedded control, machine learning, and autonomous systems. She aims to bridge theoretical foundations with practical engineering applications while advancing intelligent autonomous systems and robust decentralized control methodologies for complex environments.

  • From 07/2021 – To 02/2027: Ph.D., Indian Institute of Technology, Bombay, India
    Dissertation/Thesis Title: Robust, Safe, Communication-free, and Decentralized Swarm Techniques in GPS-denied Environments
  • From 07/2019 – To 06/2021: M.Tech, National Institute of Technology, Warangal, India
    Dissertation/Thesis Title: Control of Blood Glucose Level for a Type-I Diabetic patient- A Comparative Study
  • From 07/2013 – To 06/2017: B.E., SATI, Vidisha, India
    Dissertation/Thesis Title: Robohost: An RF-based line following navigation mechanism for order reception and delivery.

  • Jain, S., and Vachhani, L., 2026. DESNA: A Local Sensing-Based Framework for Decentralized Swarm Navigation in Cluttered Indoor Environments. (Under peer review)
  • Jain, S., and Vachhani, L., 2026. Stability of Decentralized Swarm Clustering under Sensing-Driven Switching. (Under peer review)
  • Jain, S., Katole, R. and Vachhani, L., 2026. Swarm self-clustering for communication-denied environments without global positioning. Advanced Robotics, pp.1-25. https://doi.org/10.1080/01691864.2026.2664845.
  • S. Jain and L. Vachhani, “Guided Swarm Self-Clustering in Safe Area,” 2025 IEEE/SICE International Symposium on System Integration (SII), Munich, Germany, 2025, pp. 1530-1535, doi: 10.1109/SII59315.2025.10871028.

  • July 2022 – May 2026: Teaching Assistant, Centre for Systems and Control, IIT Bombay, India
  • Feb 2026 – July 2026:  Teaching Assistant, Centre for Machine Intelligence and Data Science, IIT Bombay, India

  • Communication-free and scalable swarm autonomy: Distributed algorithms with provable scalability, convergence, and robustness under sensing constraints.
  • Safe and explainable reinforcement learning for Swarm Robotics: Hybrid architectures combining lattice or topological abstractions, deep RL, control barrier functions, and formal safety constraints.
  • Sim-to-real validation and heterogeneous robots: Reproducible swarm benchmarks, hardware-validated algorithms, and transferable autonomy frameworks.
  • Distributed estimation and resilient autonomy: Lightweight local state estimation, uncertainty-aware planning, and robust decentralized control.
Make an enquiry Chat with a student