Learning Interactive Behaviors for Musculoskeletal Robots Using Bayesian Interaction Primitives

by   Joseph Campbell, et al.
Arizona State University
Kyushu Institute of Technology
Osaka University

Musculoskeletal robots that are based on pneumatic actuation have a variety of properties, such as compliance and back-drivability, that render them particularly appealing for human-robot collaboration. However, programming interactive and responsive behaviors for such systems is extremely challenging due to the nonlinearity and uncertainty inherent to their control. In this paper, we propose an approach for learning Bayesian Interaction Primitives for musculoskeletal robots given a limited set of example demonstrations. We show that this approach is capable of real-time state estimation and response generation for interaction with a robot for which no analytical model exists. Human-robot interaction experiments on a 'handshake' task show that the approach generalizes to new positions, interaction partners, and movement velocities.


page 1

page 4

page 5

page 8


Trajectory Advancement for Robot Stand-up with Human Assistance

Physical interactions are inevitable part of human-robot collaboration t...

Probabilistic Multimodal Modeling for Human-Robot Interaction Tasks

Human-robot interaction benefits greatly from multimodal sensor inputs a...

Learning and Blending Robot Hugging Behaviors in Time and Space

We introduce an imitation learning-based physical human-robot interactio...

Dynamic Robot Motion Prediction Updates in Physical Human-Robot Interactive Tasks

Human-robot collaboration is on the rise. Robots need to increasingly im...

Learning Skills from Demonstrations: A Trend from Motion Primitives to Experience Abstraction

The uses of robots are changing from static environments in factories to...

Shutter, the Robot Photographer: Leveraging Behavior Trees for Public, In-the-Wild Human-Robot Interactions

Deploying interactive systems in-the-wild requires adaptability to situa...

Building an Affordances Map with Interactive Perception

Robots need to understand their environment to perform their task. If it...

Please sign up or login with your details

Forgot password? Click here to reset