Data-efficient Learning of Morphology and Controller for a Microrobot

by   Thomas Liao, et al.

Robot design is often a slow and difficult process requiring the iterative construction and testing of prototypes, with the goal of sequentially optimizing the design. For most robots, this process is further complicated by the need, when validating the capabilities of the hardware to solve the desired task, to already have an appropriate controller, which is in turn designed and tuned for the specific hardware. In this paper, we propose a novel approach, HPC-BBO, to efficiently and automatically design hardware configurations, and evaluate them by also automatically tuning the corresponding controller. HPC-BBO is based on a hierarchical Bayesian optimization process which iteratively optimizes morphology configurations (based on the performance of the previous designs during the controller learning process) and subsequently learns the corresponding controllers (exploiting the knowledge collected from optimizing for previous morphologies). Moreover, HPC-BBO can select a "batch" of multiple morphology designs at once, thus parallelizing hardware validation and reducing the number of time-consuming production cycles. We validate HPC-BBO on the design of the morphology and controller for a simulated 6-legged microrobot. Experimental results show that HPC-BBO outperforms multiple competitive baselines, and yields a 360% reduction in production cycles over standard Bayesian optimization, thus reducing the hypothetical manufacturing time of our microrobot from 21 to 4 months.


page 1

page 4

page 5

page 6


Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning

Humans and animals are capable of quickly learning new behaviours to sol...

On Designing a Learning Robot: Improving Morphology for Enhanced Task Performance and Learning

As robots become more prevalent, optimizing their design for better perf...

Using Simulation to Improve Sample-Efficiency of Bayesian Optimization for Bipedal Robots

Learning for control can acquire controllers for novel robotic tasks, pa...

Neural fidelity warping for efficient robot morphology design

We consider the problem of optimizing a robot morphology to achieve the ...

Bayesian Optimization in Variational Latent Spaces with Dynamic Compression

Data-efficiency is crucial for autonomous robots to adapt to new tasks a...

A systems design approach for the co-design of a humanoid robot arm

Classically, the development of humanoid robots has been sequential and ...

C^2:Co-design of Robots via Concurrent Networks Coupling Online and Offline Reinforcement Learning

With the rise of computing power, using data-driven approaches for co-de...

Please sign up or login with your details

Forgot password? Click here to reset