Nick Cheney

Evolving Soft Robots in Tight Spaces

Soft robots have become increasingly popular in recent years -- and justifiably so. Their compliant structures and (theoretically) infinite degrees of freedom allow them to undertake tasks which would be impossible for their rigid body counterparts, such as conforming to uneven surfaces, efficiently distributing stress, and passing through small apertures. Previous work in the automated deign of soft robots has shown examples of these squishy creatures performing traditional robotic task like locomoting over flat ground. However, designing soft robots for traditional robotic tasks fails to fully utilize their unique advantages. In this work, we present the first example of a soft robot evolutionarily designed for reaching or squeezing through a small aperture -- a task naturally suited to its type of morphology. We optimize these creatures with the CPPN-NEAT evolutionary algorithm, introducing a novel implementation of the algorithm which includes multi-objective optimization while retaining its speciation feature for diversity maintenance. We show that more compliant and deformable soft robots perform more effectively at this task than their less flexible counterparts. This work serves mainly as a proof of concept, but we hope that it helps to open the door for the better matching of tasks with appropriate morphologies in robotic design in the future.

Evolutionary Developmental Soft Robotics As a Framework to Study Intelligence and Adaptive Behavior in Animals and Plants

In this paper a comprehensive methodology and simulation framework will be reviewed, designed in order to study the emergence of adaptive and intelligent behavior in generic soft-bodied creatures. By incorporating artificial evolutionary and developmental processes, the system allows to evolve complete creatures (brain, body, developmental properties, sensory and control system, etc.) for different task environments. Whether the evolved creatures will resemble animals or plants is in general not known a priori, and depends on the specific task environment set up by the experimenter. In this regard, the system may offer a unique opportunity to explore differences and similarities between these two worlds. Different material properties can be simulated and optimized, from a continuum of soft/stiff materials, to the interconnection of heterogeneous structures, both found in animals and plants alike. The adopted genetic encoding and simulation environment are particularly suitable in order to evolve distributed sensory and control systems, which play a particularly important role in plants. After a general description of the system some case studies will be presented, focusing on the emergent properties of the evolved creatures. Particular emphasis will be on some unifying concepts that are thought to play an important role in the emergence of intelligent and adaptive behavior across both the animal and plant kingdoms, such as morphological computation and morphological developmental plasticity. Overall, with this paper we hope to draw attention on set of tools, methodologies, ideas and results which may be relevant to researchers interested in plant-inspired robotics and intelligence.

How morphological development can guide evolution

Organisms result from adaptive processes interacting across different time scales. One such interaction is that between development and evolution. Models have shown that development sweeps over several traits in a single agent, sometimes exposing promising static traits. Subsequent evolution can then canalize these rare traits. Thus, development can, under the right conditions, increase evolvability. 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. This allows evolution to continue climbing fitness gradients by tinkering with the developmental programs for controllers within these permissive body plans. This exposes a previously unknown detail about the Baldwin effect: instead of all useful traits becoming genetically assimilated, only traits that render the agent robust to changes in other traits become assimilated. We refer to this as differential canalization. This finding also has implications for the evolutionary design of artificial and embodied agents such as robots: robots robust to internal changes in their controllers may also be robust to external changes in their environment, such as transferal from simulation to reality or deployment in novel environments.

Simulating the evolution of soft and rigid-body robots

In evolutionary robotics, evolutionary methods are used to optimize robots to different tasks. Because using physical robots is costly in terms of both time and money, simulated robots are generally used instead. Most physics engines are written in C++ which can be a barrier for new programmers. In this paper we present two Python wrappers, Pyrosim and Evosoro, around two well used simulators, Open Dynamics Engine (ODE) and Voxelyze/VoxCAD, which respectively handle rigid and soft bodied simulation. Python is an easier language to understand so more time can be spent on developing the actual experiment instead of programming the simulator.

Scalable co-optimization of morphology and control in embodied machines

Evolution sculpts both the body plans and nervous systems of agents together over time. By contrast, in artificial intelligence and robotics, a robots body plan is usually designed by hand, and control policies are then optimized for that fixed design. The task of simultaneously co-optimizing the morphology and controller of an embodied robot has remained a challenge. In psychology, the theory of embodied cognition posits that behaviour 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 behavioural performance. Here, we further examine this hypothesis and demonstrate a technique for ‘morphological innovation protection’, which temporarily reduces selection pressure on recently morphologically changed individuals, thus enabling evolution some time to ‘readapt’ to the new morphology with subsequent control policy mutations. We show the potential for this method to avoid local optima and converge to similar highly fit morphologies across widely varying initial conditions, while sustaining fitness improvements further into optimization. While this technique is admittedly only the first of many steps that must be taken to achieve scalable optimization of embodied machines, we hope that theoretical insight into the cause of evolutionary stagnation in current methods will help to enable the automation of robot design and behavioural training—while simultaneously providing a test bed to investigate the theory of embodied cognition.