Advancing the Science of
Intelligent Agents

A research collective pushing the boundaries of agentic AI, reinforcement learning, and adaptive systems for real-world impact.

Research Area 01

Agentic AI Systems

Our core research focuses on developing AI agents capable of autonomous decision-making, planning, and execution in dynamic environments. We explore novel architectures that combine reasoning, memory, and tool use to create agents that can operate independently while remaining aligned with human values.

Research Area 02

Multi-Agent Coordination

Multi-agent systems represent the future of scalable AI, where multiple specialized agents collaborate to solve problems beyond individual capabilities. Our research addresses coordination, communication protocols, and emergent behaviors in agent societies.

Research Area 03

Reinforcement Learning

Led by Dr. Deepali Salwan (PhD in Deep Reinforcement Learning), our RL research focuses on developing robust algorithms that can learn optimal behaviors in uncertain, dynamic environments with applications spanning from robotics to healthcare.

Research Area 04

Healthcare AI

Our healthcare AI research combines machine learning, robotics, and human factors to develop intelligent systems that improve patient outcomes, enhance medical devices, and support clinical decision-making.

Research Focus

1. Deep Reinforcement Learning for Medical Devices

Algorithm development for prosthetic control (DDPG, PPO)
Real-time learning and adaptation
Transfer from simulation to physical devices

2. Intelligent Prosthetic Systems

Personalized gait control
Sensor-driven adaptive systems
User-specific optimization

3. Healthcare Robotics

Rehabilitation robotics
AI-powered assistive devices
Quality of life improvements through technology

4. Control Systems & Algorithms

Model-based vs model-free approaches
Real-time system constraints
Safety-critical algorithm design

Citations & Impact

Total Citations: 13+ (Google Scholar)

Research Impact: Pioneering work applying deep RL to prosthetic knee control

Collaboration: Multi-institutional partnerships (Sharda University, PDUNIPPD)

Research Focus

1. Deep Reinforcement Learning for Medical Devices

Algorithm development for prosthetic control (DDPG, PPO)
Real-time learning and adaptation
Transfer from simulation to physical devices

2. Intelligent Prosthetic Systems

Personalized gait control
Sensor-driven adaptive systems
User-specific optimization

3. Healthcare Robotics

Rehabilitation robotics
AI-powered assistive devices
Quality of life improvements through technology

4. Control Systems & Algorithms

Model-based vs model-free approaches
Real-time system constraints
Safety-critical algorithm design

Citations & Impact

Total Citations: 13+ (Google Scholar)

Research Impact: Pioneering work applying deep RL to prosthetic knee control

Collaboration: Multi-institutional partnerships (Sharda University, PDUNIPPD)

Advancing the Science of
Intelligent Agents

Agentic AI Systems

Multi-Agent Coordination

Reinforcement Learning

Healthcare AI

Research Focus

1. Deep Reinforcement Learning for Medical Devices

2. Intelligent Prosthetic Systems

3. Healthcare Robotics

4. Control Systems & Algorithms

Citations & Impact

Selected Papers

Challenges with Reinforcement Learning in Prosthesis

Prosthetic Knee Joint - A Survey and Using Reinforcement Learning for Natural Gait

DDPG vs PPO in Prosthetics

Robotics and Artificial Intelligence for Rehabilitation

Role of Artificial Intelligence and Machine Learning in Resolving the Issues and Challenges with Prosthetic Knees

Advancing the Science of
Intelligent Agents

Agentic AI Systems

Multi-Agent Coordination

Reinforcement Learning

Healthcare AI

Research Focus

1. Deep Reinforcement Learning for Medical Devices

2. Intelligent Prosthetic Systems

3. Healthcare Robotics

4. Control Systems & Algorithms

Citations & Impact

Selected Papers

Challenges with Reinforcement Learning in Prosthesis

Prosthetic Knee Joint - A Survey and Using Reinforcement Learning for Natural Gait

DDPG vs PPO in Prosthetics

Robotics and Artificial Intelligence for Rehabilitation

Role of Artificial Intelligence and Machine Learning in Resolving the Issues and Challenges with Prosthetic Knees

Advancing the Science of Intelligent Agents

Agentic AI Systems

Multi-Agent Coordination

Reinforcement Learning

Healthcare AI

Research Focus

1. Deep Reinforcement Learning for Medical Devices

2. Intelligent Prosthetic Systems

3. Healthcare Robotics

4. Control Systems & Algorithms

Citations & Impact

Selected Papers

Challenges with Reinforcement Learning in Prosthesis

Prosthetic Knee Joint - A Survey and Using Reinforcement Learning for Natural Gait

DDPG vs PPO in Prosthetics

Robotics and Artificial Intelligence for Rehabilitation

Role of Artificial Intelligence and Machine Learning in Resolving the Issues and Challenges with Prosthetic Knees

Advancing the Science of Intelligent Agents

Agentic AI Systems

Multi-Agent Coordination

Reinforcement Learning

Healthcare AI

Research Focus

1. Deep Reinforcement Learning for Medical Devices

2. Intelligent Prosthetic Systems

3. Healthcare Robotics

4. Control Systems & Algorithms

Citations & Impact

Selected Papers

Challenges with Reinforcement Learning in Prosthesis

Prosthetic Knee Joint - A Survey and Using Reinforcement Learning for Natural Gait

DDPG vs PPO in Prosthetics

Robotics and Artificial Intelligence for Rehabilitation

Role of Artificial Intelligence and Machine Learning in Resolving the Issues and Challenges with Prosthetic Knees

Advancing the Science of
Intelligent Agents

Advancing the Science of
Intelligent Agents