Learning User-Preferred Mappings for Intuitive Robot Control

By Mengxi Li, Dylan P. Losey, Jeannette Bohg, Dorsa Sadigh. 2020

26 citations recorded by the source corpus.

When humans control drones, cars, and robots, we often have some preconceived notion of how our inputs should make the system behave. Existing approaches to teleoperation typically assume a one-size-fits-all approach, where the designers pre-define a mapping between human inputs and robot actions, and every user must adapt to this mapping over repeated interactions. Instead, we propose a personalized method for learning the human’s preferred or preconceived mapping from a few robot queries. Given a robot controller, we identify an alignment model that transforms the human’s inputs so that the controller’s output matches their expectations. We make this approach data-efficient by recognizing that human mappings have strong priors: we expect the input space to be proportional, reversable, and consistent. Incorporating these priors ensures that the robot learns an intuitive mapping from few examples. We test our learning approach in robot manipulation tasks inspired by assistive settings, where each user has different personal preferences and physical capabilities for teleoperating the robot arm. Our simulated and experimental results suggest that learning the mapping between inputs and robot actions improves objective and subjective performance when compared to manually defined alignments or learned alignments without intuitive priors. The supplementary video showing these user studies can be found at: https://youtu.be/rKHka0_48-Q

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Social Psychology, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Siddharth Karamcheti
2. Dorsa Sadigh
3. Percy Liang
4. Megha Srivastava
5. A. Zhai
6. Dylan P. Losey
7. Mohit Bansal
8. Luc Van Gool

In Control and Systems Engineering

1. Siddharth Karamcheti
2. Percy Liang
3. Megha Srivastava
4. Dorsa Sadigh
5. A. Zhai
6. Dylan P. Losey

In Social Psychology

1. Siddharth Karamcheti
2. Dorsa Sadigh
3. Dylan P. Losey
4. Percy Liang
5. Megha Srivastava
6. A. Zhai

In Reinforcement Learning

1. Siddharth Karamcheti
2. Dorsa Sadigh
3. Percy Liang
4. Megha Srivastava
5. A. Zhai
6. Dylan P. Losey

Citations in the corpus

• LILA: Language-Informed Latent Actions (2021, methodology): “Instead, we adopt learned latent actions [5, 7, 8, 27, 28] a framework that uses conditional auto-encoders [29] to learn task-specific latent “action” spaces from demonstrations.”
• Learning latent actions to control assistive robots (2021, unknown): “This paper combines our earlier work from [31,26,30].”
• Learning Visually Guided Latent Actions for Assistive Teleoperation (2021, methodology): “, 2020), as well as personalized the mapping of the learned latent space to individual users (Li et al., 2020).”