Zero-Shot Visual Imitation
Deepak Pathak, Parsa Mahmoudieh, Guanghao Luo et al. · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2018
Imitating expert demonstration is a powerful mechanism for learning to perform tasks from raw sensory observations. The current dominant paradigm in learning from demonstration (LfD) [3,16,19,20] requires the expert to either manually move the robot joints (i.e., kinesthetic teaching) or teleoperate the robot to execute the desired task. The expert typically provides multiple demonstrations of a task at training time, and this generates data in the form of observation-action pairs from the agent's point of view. The agent then distills this data into a policy for performing the task of interest. Such a heavily supervised approach, where it is necessary to provide demonstrations by controlling the robot, is incredibly tedious for the human expert. Moreover, for every new task that the robot needs to execute, the expert is required to provide a new set of demonstrations.
Cited by 180 works. doi:10.1109/cvprw.2018.00278 Open-access PDF
Authors
- Deepak Pathak
- Parsa Mahmoudieh
- Guanghao Luo
- Pulkit Agrawal
- Dian Chen
- Evan Shelhamer
- Jitendra Malik
- Alexei A. Efros
- Trevor Jackson Darrell
References
- A survey of robot learning from demonstration
- Is imitation learning the route to humanoid robots?
- Curiosity-Driven Exploration by Self-Supervised Prediction
- Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours
- Relative end-effector control using Cartesian position based visual servoing
- Forward models: Supervised learning with a distal teacher
- Active, uncalibrated visual servoing
- Time-Contrastive Networks: Self-Supervised Learning from Video
- Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation
- Combining self-supervised learning and imitation for vision-based rope manipulation