Publications (23)
Reinforcement learning for freeform robot design
Muhan Li, David Matthews, Sam Kriegman
Inspired by the necessity of morphological adaptation in animals, a growing body of work has attempted to expand robot training to encompass physical aspects of a robot's design. H…
Robots that redesign themselves through kinematic self-destruction
Chen Yu, Sam Kriegman
Every robot built to date was predesigned by an external process, prior to deployment. Here we show a robot that actively participates in its own design during its lifetime. Starti…
Automated shapeshifting for function recovery in damaged robots
Sam Kriegman, Stephanie Walker, Dylan Shah +3
A robot's mechanical parts routinely wear out from normal functioning and can be lost to injury. For autonomous robots operating in isolated or hostile environments, repair from a…
Scale invariant robot behavior with fractals
Sam Kriegman, Amir Mohammadi Nasab, Douglas Blackiston +4
Robots deployed at orders of magnitude different size scales, and that retain the same desired behavior at any of those scales, would greatly expand the environments in which the r…
Generating Freeform Endoskeletal Robots
Muhan Li, Lingji Kong, Sam Kriegman
The automatic design of embodied agents (e.g. robots) has existed for 31 years and is experiencing a renaissance of interest in the literature. To date however, the field has remai…
Creating manufacturable blueprints for coarse-grained virtual robots
Zihan Guo, Muhan Li, Shuzhe Zhang +1
Over the past three decades, countless embodied yet virtual agents have freely evolved inside computer simulations, but vanishingly few were realized as physical robots. This is be…
Interoceptive robustness through environment-mediated morphological development
Sam Kriegman, Nick Cheney, Francesco Corucci +1
Typically, AI researchers and roboticists try to realize intelligent behavior in machines by tuning parameters of a predefined structure (body plan and/or neural network architectu…
A Minimal Developmental Model Can Increase Evolvability in Soft Robots
Sam Kriegman, Nick Cheney, Francesco Corucci +1
Different subsystems of organisms adapt over many time scales, such as rapid changes in the nervous system (learning), slower morphological and neurological change over the lifetim…
Evolving Spatially Aggregated Features from Satellite Imagery for Regional Modeling
Sam Kriegman, Marcin Szubert, Josh C. Bongard +1
Satellite imagery and remote sensing provide explanatory variables at relatively high resolutions for modeling geospatial phenomena, yet regional summaries are often desirable for…
Scalable sim-to-real transfer of soft robot designs
Sam Kriegman, Amir Mohammadi Nasab, Dylan Shah +5
The manual design of soft robots and their controllers is notoriously challenging, but it could be augmented---or, in some cases, entirely replaced---by automated design tools. Mac…
Computational Design of a Low-Visibility UAV Using a Human-Aligned Perceptual Metric
Jingxian Wang, Chen Yu, David Matthews +3
We introduce Phantom Twist, a type of single-propeller UAV designed to achieve low visibility through high-speed spinning and the exploitation of motion blur. We develop a two-stag…
Accelerated co-design of robots through morphological pretraining
Luke Strgar, Sam Kriegman
The co-design of robot morphology and neural control typically requires using reinforcement learning to approximate a unique control policy gradient for each body plan, demanding m…
Word2vec to behavior: morphology facilitates the grounding of language in machines
David Matthews, Sam Kriegman, Collin Cappelle +1
Enabling machines to respond appropriately to natural language commands could greatly expand the number of people to whom they could be of service. Recently, advances in neural net…
Combating catastrophic forgetting with developmental compression
Shawn L. E. Beaulieu, Sam Kriegman, Josh C. Bongard
Generally intelligent agents exhibit successful behavior across problems in several settings. Endemic in approaches to realize such intelligence in machines is catastrophic forgett…
Evolution and learning in differentiable robots
Luke Strgar, David Matthews, Tyler Hummer +1
The automatic design of robots has existed for 30 years but has been constricted by serial non-differentiable design evaluations, premature convergence to simple bodies or clumsy b…
ECo-MoE: Embodiment-Conditioned Mixture of Experts Increases the Evolvability of Robots
Yibin Wang, Muhan Li, Zihan Guo +1
In this paper, we introduce a model of evolution and learning in robots that co-optimizes a distribution of latent design vectors (genotypes) and a mixture of control experts (neur…
A soft robot that adapts to environments through shape change
Dylan S. Shah, Joshua P. Powers, Liana G. Tilton +3
Many organisms, including various species of spiders and caterpillars, change their shape to switch gaits and adapt to different environments. Recent technological advances, rangin…
Agile legged locomotion in reconfigurable modular robots
Chen Yu, David Matthews, Jingxian Wang +4
Legged machines are becoming increasingly agile and adaptive but they have so far lacked the morphological diversity of legged animals, which have been rearranged and reshaped to f…
A non-cubic space-filling modular robot
Tyler Hummer, Sam Kriegman
Space-filling building blocks of diverse shape permeate nature at all levels of organization, from atoms to honeycombs, and have proven useful in artificial systems, from molecular…
Efficient automatic design of robots
David Matthews, Andrew Spielberg, Daniela Rus +2
Robots are notoriously difficult to design because of complex interdependencies between their physical structure, sensory and motor layouts, and behavior. Despite this, almost ever…
Embodiment dictates learnability in neural controllers
Joshua Powers, Ryan Grindle, Sam Kriegman +3
Catastrophic forgetting continues to severely restrict the learnability of controllers suitable for multiple task environments. Efforts to combat catastrophic forgetting reported i…
How morphological development can guide evolution
Sam Kriegman, Nick Cheney, Josh Bongard
Organisms result from adaptive processes interacting across different time scales. One such interaction is that between development and evolution. Models have shown that developmen…
Glamour muscles: why having a body is not what it means to be embodied
Shawn L. Beaulieu, Sam Kriegman
Embodiment has recently enjoyed renewed consideration as a means to amplify the faculties of smart machines. Proponents of embodiment seem to imply that optimizing for movement in…