Designing novel robots that can cope with a specific task is a challenging problem because of the enormous design space that involves both morphological structures and control mechanisms. To this end, we present a computational method for automating the design of modular robots. Our method employs a genetic algorithm to evolve robotic structures as an outer optimization, and it applies a reinforcement learning algorithm to each candidate structure to train its behavior and evaluate its potential learning ability as an inner optimization. The size of the design space is reduced significantly by evolving only the robotic structure and by performing behavioral optimization using a separate training algorithm compared to that when both the structure and behavior are evolved simultaneously. Mutual dependence between evolution and learning is achieved by regarding the mean cumulative rewards of a candidate structure in the reinforcement learning as its fitness in the genetic algorithm. Therefore, our method searches for prospective robotic structures that can potentially lead to near-optimal behaviors if trained sufficiently. We demonstrate the usefulness of our method through several effective design results that were automatically generated in the process of experimenting with actual modular robotics kit.

Popular virtual reality systems today allow us to experience highly immersive applications in which virtual objects are realistically perceived via stereoscopic displays and can be directly manipulated based on hand-eye coordination in a very similar way as in the real world. However, the insufficiency of sensory feedback as well as the limited degrees-of-freedom of input motion still hinders precise and elaborate manipulation in virtual reality. Aiming at more precise 3D manipulation, we present a new method of extending the user's spatial perception ability with the 'virtual mirrors', which expose the hidden spatial information of given virtual scenes to the user. The movement of a virtual mirror is automatically controlled by solving an optimization problem iteratively, in which the objective function prefers the placement of the mirror that can highlight the spatial relationship between the manipulated object and the object nearest to it. The optimization process is handled efficiently for each time step based on our method for finding the closest gap between any two objects based on the OBB (oriented bounding box) trees and our samplingbased approximate approach to the optimization problem. The usefulness of our method is demonstrated by several pilot applications under various usage scenarios, such as assembling construction toys and solving 3D dissection puzzles. The quantitative results of our user study show that the virtual mirror is very helpful in increasing the precision in 3D manipulation tasks in virtual reality.

Due to the maker movement and 3D printers, people nowadays can directly fabricate mechanical devices that meet their own objectives. However, it is not intuitive to identify the relationship between specific mechanical movements and mechanical structures that facilitate such movements. This paper presents an interactive system that can enable users to easily create and experiment with desired mechanical assemblies via direct manipulation interfaces in virtual reality, as well as to intuitively explore design space through repeated application of the crossover operation, which is used at the core of the genetic algorithm. Specifically, a mechanical assembly in our system is genetically encoded as a undirected graph structure in which each node corresponds to a mechanical part and each edge represents the connection between parts. As the user selects two different mechanical assemblies and commands the crossover operation, each of their corresponding graphs is split into two subgraphs and those subgraphs are recombined to generate the next-generation mechanical assemblies. The user can visually examine new mechanical assemblies, save assemblies that are closer to objectives, and remove the others. Based on our experiments, in which non-expert participants were asked to achieve a challenging design objective, it was verified that the proposed interface exhibited significantly effective performance.