Embedded Files
Key research areas
Current:
1) Embodied AI (Generative AI)
a. Robot Manipulation/Grasping
b. Locomotion
2) Machine Learning for Robotic and Control Applications
a. Reinforcement Learning
b. Imitation Learning
c. Learning from Demonstration
3) Biomimetics/bioinspiration:
a. Robotic Manta Ray
b. Soft grippers
4) Autonomous systems:
a. Humanoid Robots
b. AMR/AGV
b. Unmanned Surface Vehicles
c. Legged robots
Previous:
1) Humanoid Robots: Robot Design, Bipedal Walking
2) Exoskeleton/Assistive Device for Lower Extremities
3) Actuator design
Robotic Manta Ray
Manta rays are very efficient swimmers which are able to travel at high speed over long distances. This research focuses on the design, experiment and prototype testing of a propulsive mechanism for Robot Manta Ray. The propulsive mechanism and the pectoral fins of the Robot Manta Ray were designed based on some of the hydrodynamic concepts of manta ray locomotion. The designs focus on simplicity and utilize passive flexibility to generate high forward thrust while achieving high energy efficiency.
Video: Mantadroid Mk 1
Figure: Experimental set-up
Unmanned Surface Vehicles (Autonomous Boat)
The purpose of this project is to develop a sensory system for a USV with the capabilities of detecting close range obstacles under varying weather conditions. Given the proliferation in sensors development, different combination of sensors (vision, LIDAR, etc) will be deployed to provide effective tools for close range OA. Sensor fusion algorithms will be used to generate stable obstacles information for the USV in the real-time. A new obstacle avoidance algorithm that considers both the velocity of the obstacle and kinematic constraint of the vehicle will be developed.
Figure: Unmanned Surface Vehicle performing autonomous tasks
Humanoid / Bipedal Robot
The aim of this research is to design and build bipedal robots that can achieve dynamic walking on level and rough terrain. We adopt different designs and apply different walking control algorithms to the robots. Learning paradigms like reinforcement learning will also be adopted in the control algorithm. From experimentation, we wish to extract rules for general bipedal walking.
Link to NUS Legged Locomotion Group website.
Video: NUSBIP-III (ASLAN) first implementation
Video: Turning and walking (ASLAN)
Figure: Team RO-PE from National University of Singapore won the first prize in “dribble and kick” and “Technical Challenge” in adult-size, humanoid league, RoboCup 2010, Singapore (1 July 2010)
Figure: NUSBIP-III and the research team (2010)
Figure: NUSBIP-III (16 Jan 2009)
Figure: NUSBIP-III (14 Nov 2008)
Robot hand
The aim of this research is to design biomimetic robot hand for humanoid robot. It is based on underactuated approach which enables the design to be compact and lightweight.
Video: Prototype of ASLAN’s hand (developed based on rapid prototyping process by Final Year Project student: Timothy Gan)
Video: Updated Prototype of ASLAN’s hand by Final Year Project student, Shi-Yuan Tang.
Figure: ASLAN’s hand (version 2)
Exoskeleton / Assistive Device
This research aims to develop low cost lower extremities assistive device for rehabilitation and human strength augmentation.
Applications:
•Load carrying (Previous collaboration with DMERI@DSO)
•Rehabilitation
Figure: Lower Extremity Assistive Device (LEAD)
Figure: Knee Active Assistive Device (KAAD)
Actuator Design: Force Control Actuators
Legged robots is required to interact with the surrounding environment. In such applications, good actuator force control is very desirable. One such actuator design is called the series elastic actuator which is adopted by MIT Leg Laboratory. It is an actuator that is connected to the external load through an elastic component. The desired force on the load is achieved by controlling the deflection of the elastic component. Series elastic actuators have many desirable properties like high bandwidth, low output impedance, shock absorption capability, etc. This research involves the design and control of the force-controlled actuator. We are interested to compare different designs, for example, rotary versus linear elastic components, steel versus elastomer elastic material, linear versus nonlinear spring. The actuator will eventually be applied to legged robots or robot manipulator which requires force control.
Collaboration: SIMTech
Figure: Variable stiffness module for force control actuator
General Legged Robots
The aim of this research is to design and build legged machine that have more than two legs. We are interested to study different walking or running gaits. By building these machines, we hope to understand the mechanisms for locomotion adopted by the biological counterparts. We also wish to build machines that are able to walk dynamically and robustly over rough terrain.
Page updated
Google Sites
Report abuse