Agile Locomotion & Manipulation
Goals
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 control algorithm design, perception of dynamic legged locomotion and manipulation, and mechanical design. The goals of this team are (i) design whole-body control algorithms humanoid robot locomotion and manipulation; and (ii) sensing, control, and planning algorithms for locomotion over real-world rough terrain.
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 motivated undergraduate students who are interested in robotics learning, control and mechanical design. Please visit our lab website for on-going research projects.
Here is a list of our past publications. Visit our website for the full list.
Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulation & Video
Learn to Teach: Sample-Efficient Privileged Learning for Humanoid Locomotion over Diverse Terrains & Video
Robust-Locomotion-by-Logic: Perturbation-Resilient Bipedal Locomotion via Signal Temporal Logic Guided Model Predictive Control & Video
SEEC: Stable End-Effector Control with Model-Enhanced Residual Learning for Humanoid Loco-Manipulation & Video
STATE-NAV: Stability-Aware Traversability Estimation for Bipedal Navigation on Rough Terrain
Partners/Sponsors
National Science Foundation
Link(s)
Methods and Technologies
- Reinforcement Learning
- Robot Kinematics and Dynamics
- Programming and Software Engineering
- Control System Design
- Machine Learning
- Optimization Algorithm
- Mechanical Design
Majors Sought
Computing: Computer Science
Engineering: Aerospace Engineering, Biomedical Engineering, Computer Engineering, Electrical Engineering, Industrial Engineering, Mechanical Engineering
Sciences: Mathematics, Physics
Preferred Interests and Preparation
ME: Background/interest in mechanical design, mechatronics, control, dynamics, physics-based simulation.
CS: Background/interest in machine learning, reinforcement learning, robotic learning, perception, physics-based simulation, graphics.
EE: Background/interest in embedded system, signal processing, control, programming, software, physics-based simulation.
AE, BME, Physics: Background/interest in control, dynamics, programming, software, physics-based simulation.
ISyE, Math: Background/interest in machine learning and optimization.
Day, Time & Location
Full Team Meeting:
Contact the team mentor for specific time. Team does not meet on Monday at 8pm. Each individual sub-team will manage their own time separately, and the meeting time is set up by the sub-team. Subteam meetings scheduled after classes begin. Monday
TBD
Subteam meetings scheduled after classes begin.