1. Multi-Contact Variable Compliance Manipulation in Extreme Clutter, DARPA-M3 (2011-2014)

As a part of this project, the bigger goal is to develop new foundational capabilities for robot manipulation that assume contact is inevitable and desirable, and use full-body force-sensing skin with compliant actuation. I am currently using the robot forearm skin to infer mechanical properties of environment objects during incidental contact such that this information can be used intelligently for effective manipulation in cluttered environments. Details of the DARPA-M3 initiative can be found here.

2. Partnered Rehabilitative Movement: Cooperative Human-Robot Interactions for Motor Assistance, Learning, and Communication, NSF EFRI-M3C (Present)

The vision of this project is to develop caregiver robots that interact fluidly and flexibly with humans during functional motor activities, while providing motor assistance, enhancement, and communication to facilitate motor learning. However, we currently lack theories to understand how rehabilitation and movement therapists provide timely and appropriate physical feedback and assistance to improve mobility in individuals with motor impairments. To develop devices that could accompany an individual as both assistant and movement therapist, our goal is to study human motor coordination during cooperative physical interactions with a humanoid assistive robot. We will use rehabilitative partner dance as a paradigm to examine a sensory-motor theory of cooperative physical interactions relevant to walking and other functional motor activities. We will use a “partnered box step”, a constrained and defined pattern of weight shifts and directional changes, as a paradigm for a cooperative physical interaction with well-defined motor goals. Details of this project are given here.

3. Development of Robot Arm and Hand Coordinated Grasping/Manipulation Control Technology for Housework

As a part of this project, we developed a novel control law to exhibit human-motion characteristics in redundant robot arm systems for reaching tasks. This newly developed method nullifies the need for the computation of pseudo-inverse of Jacobian while the formulation and optimization of any artificial performance index is not necessary. The time-varying properties of the muscle stiffness and damping as well as the low-pass filter characteristics of human muscles have been modeled by the proposed control law. The newly developed control law uses a time-varying damping shaping matrix and a bijective joint muscle mapping function to describe the human motion characteristics for reaching motion like quasi-straight line trajectory of the end-effector and symmetric bell shaped velocity profile. The aspect of self-motion and repeatability, which are inherent in human-motion, are also analyzed and successfully modeled using the proposed method. Experiment results show the efficacy of the newly developed algorithm in
describing the human-motion characteristics. We have also done some extensive simulations by extending the above control law for hand-arm coordination tasks in reach-to-grasp tasks for grasping objects of different shapes and sizes. The experimental and simulation videos can be found here. The detailed algorithm description and results can be found here.

4. Control of a Novel Actuated and Remotely-Controlled Gastro-Intestinal Endoscope

In this project, we basically developed various control algorithms to enhance the stability and performance of remotely controlled surgical
systems in general and Gastro-intestinal endoscopes in particular. We focused on the characteristics and constraints of such systems and came up with control methodologies which can utilize the features and overcome the constraints for effective performance. One part of our work focused on a disturbance observer based method of force-estimation which can provide haptic feedback in spite of the difficulty of using force sensors in the slave side for such systems. Another part then concentrated on enhancing the perception of human operators interacting with such master-slave systems. Apart from these performance enhancement schemes, we also analyzed the stability of the system using passivity as well as absolute stability analyses for such systems interacting with soft environments and used optimization schemes to enhance the overall performance while maintaining the stability. Experiments were performed using a Phantom Premium as Master device while a 1-DOF manipulator as the slave device which showed promising results. Psychophysical experiments were also conducted to verify the efficacy of the developed algorithms in enhancing the human perception capabilities.

A part of the above project led to my Master's Thesis entitled "Analysis of Stability and Performance of Telesurgical Systems". Here is the Master's Thesis Report.

5. Fabrication of a Mobile Robot with Obstacle Avoidance (Senior Year)


In this project, we developed a mobile robot which is capable of reaching a particular destination avoiding all the obstacles in its way. We completed the design, fabrication, and control of this wheeled robot and verified the effectiveness of our algorithm using real-world experiments. 

Our main objectives in this project were:

  • Designing a mobile robot which is capable of carrying small loads.
  • Fabrication of the mobile robot.
  • Developing the Control algorithm for obstacle avoidance and simultaneous target tracking

  • Interfacing the electronic control circuit with the microprocessor through parallel port programming
  • Experiments with the wheeled mobile robot for reaching a target while avoiding obstacles
Here is the Project Report (also known as Major Project).

6. Simulation of a Cricket Playing Robot: a Neuro-Fuzzy Approach (Junior Year)


In this project, we developed an idea of a robot that is capable of playing conventional cricketing shots to any kind of ball. We basically incorporated the intelligent control techniques using a neuro-fuzzy approach and simulations were conducted to verify the working of the whole scheme.

Our main objectives in this project were:

  • Development of intelligent control methodologies for the batting robot based on fuzzy-neural approach
  • Study of cricket ball aerodynamics, taking into consideration the Drag and Magnus effects, so that its trajectory can be estimated
  • Design of a 7-DOF batting robot using a CAD software
  • Kinematic analysis of the batting robot
  • Simulation of the whole project using C++ in Windows OS
Here is the Project Report (also known as Minor Project).