Types of robot automation
- custom-built robots -> human expert programming -> Special-purpose behaviors
- General-purpose robots -> Robot learning -> General-purpose behaviors
What is robot learning?
The study of methods and principles that make robots learn from data
-> Learning is critical for taking robots to the real world.
- Robot perception: seeing and understanding the physical world
- Multimodal understanding
- 2D object detection
- Attention architectures
- 3D data processing
- Recursive state estimation
- Implicit neural representations
- Synthetic data for robot perception
- Self-supervised visual learning
- Interactive perception
- Multimodal understanding
- Robot decision making: Planning and control of robot behaviors
- Reinforcement learning
- model-free RL
- model-based RL
- Inverse RL
- Imitation learning
- Adversarial IL
- Imitation as supervised learning
- Task and Motion planning
- Hierarchical policy & neural programming
- Reinforcement learning
'Robotics & Perception > Basic' 카테고리의 다른 글
[CS391R] Overview of Robot Decision Making (0) | 2022.05.15 |
---|---|
[CS391R] Overview of Robot perception (0) | 2022.05.15 |
[Modern Robotics] Contents (0) | 2022.04.02 |
[Graphics] Obj (0) | 2022.02.02 |
[기초] 1. Introduction (0) | 2022.01.05 |