Akhil S Anand
Papers
7
Total Citations
113
H-Index
5
About
Akhil S. Anand is a leading researcher at the intersection of robotics, control theory, and machine learning, with a primary focus on developing safe, compliant, and human-like manipulation skills for autonomous systems. His work centers on variable impedance control, model-based reinforcement learning, and the integration of Control Lyapunov Functions (CLFs) and Control Barrier Functions (CBFs) to ensure safety in learning-based control. Anand’s most impactful contribution is his pioneering approach to model-based variable impedance learning control, which enables robots to adapt their stiffness in real-time—mimicking human muscle compliance—for dexterous force interaction tasks. His 2023 paper on this topic has garnered 37 citations, while his comprehensive 2021 review on safe learning using CLFs and CBFs has 33 citations, establishing foundational knowledge in the field. Notably, he also demonstrated the feasibility of using deep reinforcement learning to generate human-like walking behavior with neuromuscular models (24 citations), advancing exoskeleton and prosthesis control. Anand’s work addresses critical challenges in sample efficiency and model-bias, making reinforcement learning practical for real-world robotic systems. His research is essential reading for engineers and scientists developing next-generation, safe, and adaptive robots.
Research Focus
Key Achievements
Top Papers
- 1Model-based variable impedance learning control for robotic manipulation37 citations · 2023
- 2
- 3
- 4Data-Efficient Reinforcement Learning for Variable Impedance Control6 citations · 2024
- 5
- 6
- 7