The Laboratory for Intelligent Decision and Autonomous Robots (LIDAR) at Georgia Tech focus on planning, control, and decision-making algorithms of highly dynamic, under-actuated, and human-cooperative robots in complex environments. The VIP Team will explore the challenging research topics in mechanical design, mechatronics, control algorithm design, and perception of dynamic legged locomotion and manipulation. The goal of this team will be in the twofold: (i) design and whole-body control of a bio-inspired upper-body robot Athena for dexterous manipulation; and (ii) sensing and control algorithm design of an ostrich-like bipedal walking robot for rough terrain locomotion. Students will have opportunities to work with graduate students in the lab and explore graduate-level research at an early stage.
Issues Involved or Addressed
Our robotics research is highly interdisciplinary and demands engineering skills and research experiences across multiple schools and majors. Currently, we are looking for highly motivated undergraduate students who are interested in one of the following projects: (i) Athena upper body robot control, circuit, PCB design, and mechanical design to upgrade our current design and control system. Athena robot is a bio-inspired, highly agile upper body humanoid robot. It has more than 20 degrees-of-freedom and around 40 actuators (as shown in the robot picture). Our team has been actively improving our controller and mechanical design of this robot for dynamic and dexterous manipulation. Our goal is to integrate this upper body robot with our bipedal walking robot Cassie for unified locomotion and manipulation. Students are expected to master skills in control, circuit design, Arduino programming, basics of mechatronics and control, mechanical design, and rapid prototyping. (ii) whole-body kinematics and multi-body dynamics for the upper body Athena robot, nonlinear dynamics, and impedance control of the upper body manipulator. Students are expected to have basic knowledge in robot multi-body dynamics and control, dynamic simulator, and Python/C++ programming skills. (iii) Foot contact sensing for dynamic legged locomotion. We aim at enabling our bipedal legged robot to robustly maneuver various terrain, including sand, gravel, pine straw, and slippery surface. This project will involve fabrication, design, controller implementation of a soft, multi-sensor foot contact pad, and its system integration with our Cassie robot (tasks will include power source, communication, etc.). (iv) Vision-based perception algorithms of rough terrain locomotion and dynamic manipulation. For the locomotion project, we are interested in designing robust perception algorithms that can classify various types of terrains at runtime. For the manipulation project, the team is looking for real-time perception algorithms for agile grasping of irregular, soft, and deformable objects, and cluttered scene identification.
Methods and Technologies
Academic Majors of Interest
Preferred Interests and Preparation
ME: Background/interest in mechanical design, mechatronics, control, dynamics, physics-based simulation.
EE: Background/interest in embedded system, signal processing, control, programming, software, physics-based simulation.
CS: Background/interest in programming, software engineering, perception, physics-based simulation, graphics.
AE, BME, Physics: Background/interest in control, dynamics, programming, software, physics-based simulation.
ISyE, Math: Background/interest in machine learning and optimization.
Meeting Schedule & Location
- Mechanical Engineering
- College of Computing
- Institute for Robotics and Intelligent Machines