DMAP: a Distributed Morphological Attention Policy for Learning to Locomote with a Changing Body

by   Alberto Silvio Chiappa, et al.

Biological and artificial agents need to deal with constant changes in the real world. We study this problem in four classical continuous control environments, augmented with morphological perturbations. Learning to locomote when the length and the thickness of different body parts vary is challenging, as the control policy is required to adapt to the morphology to successfully balance and advance the agent. We show that a control policy based on the proprioceptive state performs poorly with highly variable body configurations, while an (oracle) agent with access to a learned encoding of the perturbation performs significantly better. We introduce DMAP, a biologically-inspired, attention-based policy network architecture. DMAP combines independent proprioceptive processing, a distributed policy with individual controllers for each joint, and an attention mechanism, to dynamically gate sensory information from different body parts to different controllers. Despite not having access to the (hidden) morphology information, DMAP can be trained end-to-end in all the considered environments, overall matching or surpassing the performance of an oracle agent. Thus DMAP, implementing principles from biological motor control, provides a strong inductive bias for learning challenging sensorimotor tasks. Overall, our work corroborates the power of these principles in challenging locomotion tasks.


page 5

page 9

page 21


Adjustbot: Bio-Inspired Quadruped Robot with Adjustable Posture and Undulated Body for Challenging Terradynamic Tasks

The ability to modify morphology in response to environmental changes re...

Environmental Adaptation of Robot Morphology and Control through Real-world Evolution

Robots operating in the real world will experience a range of different ...

Embodied Intelligence via Learning and Evolution

The intertwined processes of learning and evolution in complex environme...

Centralized and Decentralized Control in Modular Robots and Their Effect on Morphology

In Evolutionary Robotics, evolutionary algorithms are used to co-optimiz...

Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity

Contemporary sensorimotor learning approaches typically start with an ex...

Universal Morphology Control via Contextual Modulation

Learning a universal policy across different robot morphologies can sign...

How Morphological Computation shapes Integrated Information in Embodied Agents

The Integrated Information Theory provides a quantitative approach to co...

Please sign up or login with your details

Forgot password? Click here to reset