no code implementations • 7 Apr 2024 • Atoosa Parsa, Corey S. O'Hern, Rebecca Kramer-Bottiglio, Josh Bongard
There is growing interest in engineering unconventional computing devices that leverage the intrinsic dynamics of physical substrates to perform fast and energy-efficient computations.
no code implementations • 5 Jun 2023 • David Matthews, Andrew Spielberg, Daniela Rus, Sam Kriegman, Josh Bongard
Robots are notoriously difficult to design because of complex interdependencies between their physical structure, sensory and motor layouts, and behavior.
1 code implementation • 29 May 2023 • Atoosa Parsa, Sven Witthaus, Nidhi Pashine, Corey S. O'Hern, Rebecca Kramer-Bottiglio, Josh Bongard
Mechanical computers, wherein information processing is a material property emerging from the interaction of components with the environment, are one such class of devices.
1 code implementation • 24 May 2023 • Caitlin Grasso, Josh Bongard
Empowerment -- a domain independent, information-theoretic metric -- has previously been shown to assist in the evolutionary search for neural cellular automata (NCA) capable of homeostasis when employed as a fitness function.
1 code implementation • 27 Apr 2022 • Caitlin Grasso, Josh Bongard
Information-theoretic fitness functions are becoming increasingly popular to produce generally useful, task-independent behaviors.
1 code implementation • 19 Apr 2022 • Atoosa Parsa, Dong Wang, Corey S. O'Hern, Mark D. Shattuck, Rebecca Kramer-Bottiglio, Josh Bongard
Granular metamaterials are a promising choice for the realization of mechanical computing devices.
1 code implementation • 15 Apr 2022 • Q. Tyrell Davis, Josh Bongard
Substantial efforts have been applied to engineer CA with desired emergent properties, such as supporting gliders.
no code implementations • 18 Aug 2021 • Joshua Powers, Ryan Grindle, Lapo Frati, Josh Bongard
Efforts to combat catastrophic interference to date focus on novel neural architectures or training methods, with a recent emphasis on policies with good initial settings that facilitate training in new environments.
1 code implementation • 8 Mar 2021 • Sam Kriegman, Amir Mohammadi Nasab, Douglas Blackiston, Hannah Steele, Michael Levin, Rebecca Kramer-Bottiglio, Josh Bongard
Finally, we show that biobots can spontaneously exhibit self similar attachment geometries, thereby suggesting that self similar behavior via self similar structure may be realizable across a wide range of robot platforms in future.
1 code implementation • 23 Nov 2019 • Sam Kriegman, Amir Mohammadi Nasab, Dylan Shah, Hannah Steele, Gabrielle Branin, Michael Levin, Josh Bongard, Rebecca Kramer-Bottiglio
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.
no code implementations • 15 Oct 2019 • Joshua Powers, Ryan Grindle, Sam Kriegman, Lapo Frati, Nick Cheney, Josh Bongard
Catastrophic forgetting continues to severely restrict the learnability of controllers suitable for multiple task environments.
1 code implementation • 3 Aug 2019 • David Matthews, Sam Kriegman, Collin Cappelle, Josh Bongard
Enabling machines to respond appropriately to natural language commands could greatly expand the number of people to whom they could be of service.
1 code implementation • 22 May 2019 • Sam Kriegman, Stephanie Walker, Dylan Shah, Michael Levin, Rebecca Kramer-Bottiglio, Josh Bongard
We found that, especially in the case of "deep insult", such as removal of all four of the robot's legs, the damaged machine evolves shape changes that not only recover the original level of function (locomotion) as before, but can in fact surpass the original level of performance (speed).
1 code implementation • 16 Dec 2017 • Zahra Mahoor, Jack Felag, Josh Bongard
In this paper, we define a safe robot as one that receives a natural-language command from humans, considers an action in response to that command, and accurately predicts how humans will judge that action if is executed in reality.
1 code implementation • 20 Nov 2017 • Sam Kriegman, Nick Cheney, Josh Bongard
Here, we report on a previously unknown phenomenon when embodied agents are allowed to develop and evolve: Evolution discovers body plans robust to control changes, these body plans become genetically assimilated, yet controllers for these agents are not assimilated.
no code implementations • 17 Nov 2017 • Francesco Corucci, Nick Cheney, Francesco Giorgio-Serchi, Josh Bongard, Cecilia Laschi
Designing soft robots poses considerable challenges: automated design approaches may be particularly appealing in this field, as they promise to optimize complex multi-material machines with very little or no human intervention.
no code implementations • 19 Jun 2017 • Nick Cheney, Josh Bongard, Vytas SunSpiral, Hod Lipson
In psychology, the theory of embodied cognition posits that behavior arises from a close coupling between body plan and sensorimotor control, which suggests why co-optimizing these two subsystems is so difficult: most evolutionary changes to morphology tend to adversely impact sensorimotor control, leading to an overall decrease in behavioral performance.