teaching content
This advanced seminar introduces fundamental algorithms for creating robot systems that can autonomously perceive and manipulate objects in unstructured environments like homes, restaurants, supermarkets, etc. It addresses the complex and timely challenge of understanding and developing intelligent robotic manipulation. The seminar will discuss fundamental methods in perception (including approaches based on deep learning and approaches based on 3D geometry), planning (robot kinematics and trajectory generation, collision-free motion planning, task-and-motion planning, and planning under uncertainty), and dynamics and control (mainly force control and its variants).
The seminar will contain a combination of introductory lectures and a reading group to discuss and learn about advanced algorithmic approaches in robotics. After an introductory lecture on a new topic, small groups of students will be assigned a research paper that is fundamental for each topic (depending on the class size, there might be an alternating style). The students shall present the basic concept of the paper in class and engage in discussion regarding the presented topics.
List of topics (non-exhaustive):
Refresher on kinematics and dynamics
Pick-and-place pipeline
Object pose estimation
Grasp generation
Robot force control (stiffness, impedance, admittance)
Sampling-based motion planning
Trajectory Optimization
Task and Motion Planning
Mobile Manipulation
Prerequisites
Recommended:
The students should have fundamental knowledge in robotics, and linear algebra. Furthermore, Fundamentals of Robotics (20-00-0735-iv Fundamentals of Robotics) is recommended.
This advanced seminar introduces fundamental algorithms for creating robot systems that can autonomously perceive and manipulate objects in unstructured environments like homes, restaurants, supermarkets, etc. It addresses the complex and timely challenge of understanding and developing intelligent robotic manipulation. The seminar will discuss fundamental methods in perception (including approaches based on deep learning and approaches based on 3D geometry), planning (robot kinematics and trajectory generation, collision-free motion planning, task-and-motion planning, and planning under uncertainty), and dynamics and control (mainly force control and its variants).
The seminar will contain a combination of introductory lectures and a reading group to discuss and learn about advanced algorithmic approaches in robotics. After an introductory lecture on a new topic, small groups of students will be assigned a research paper that is fundamental for each topic (depending on the class size, there might be an alternating style). The students shall present the basic concept of the paper in class and engage in discussion regarding the presented topics.
List of topics (non-exhaustive):
Refresher on kinematics and dynamics
Pick-and-place pipeline
Object pose estimation
Grasp generation
Robot force control (stiffness, impedance, admittance)
Sampling-based motion planning
Trajectory Optimization
Task and Motion Planning
Mobile Manipulation
Prerequisites
Recommended:
The students should have fundamental knowledge in robotics, and linear algebra. Furthermore, Fundamentals of Robotics (20-00-0735-iv Fundamentals of Robotics) is recommended.
- Lehrende: Georgia Chalvatzaki
Semester: WT 2022/23