Modular robotics has been an active area of research for the last decade. In this paper, we argue that it also provides an excellent platform for education. PolyBot is a type of modular reconfigurable robot developed at PARC. The PolyKinetic/spl trade/ System provides a robotic scripting language and programming environment for controlling this type of robot. Based on experience with mentoring high school students, and running a tutorial for robotic researchers at IROS'03, we show that, PolyBot and the PolyKinetic/spl trade/ System is effective for educational activities at multiple levels. These include playing, exploring, building, programming, competing, and most of all, learning while having fun.

A common point of weakness in many path/motion planners is dealing with configuration spaces (C-spaces) that involve narrow gaps of passages. This is caused by the indirect representation of the C-space inherent in those planners. Unfortunately many real environments and tasks give rise to such situations. While a small number of planners do exist which reliably work in these environments, they in turn have problems when the robot has many controllable degrees of freedom. High degree of freedom motion in confined spaces is a typical problem encountered by PARC's PolyBot platform. The algorithm put forward in this paper is designed to work directly with the C-space obstacles' geometry, and so is not hampered by narrow passages. The planner is a homotopic one which solves general problems in n-dimensional C-space. The algorithm's theoretical characteristics are shown to compare very favourably with other contending planners in these specialised domains. Results of some preliminary testing are given.

Modular reconfigurable robots have the potential for great versatility and robustness; however, programming locomotion gaits for hundreds of modules remains a challenge. In this paper we present a formal model for programming locomotion gaits in chain-type modular robots: phase automata. A phase automation is an event-driven state automation with an initial phase delay. The phase delay is normally a real value between 0 and 1. Phase automata are compact representation of locomotion gaits and capable of being embedded and distributed across modules. The concepts of phase automata have been implemented on both PCs and embedded micro-processors. An XML script language and programming interface for phase automata are being built. Locomotion gaits programmed using phase automata have been tested both in simulation with 100+ modules and in hardware with 50+ modules.

A planner for statically-stable motion of a legged robotic vehicle over an uneven terrain is presented that can plan the footplacement of individual legs for highly cluttered terrain. A method for determining the traversability over a generic discretised height map terrain is presented. Planning is broken into two levels of refinement to reduce the overall complexity and incorporates a number of heuristics. The planner has successfully planned the motion of 6 and 8 legged configurations of the XEROX PARC PolyBot modular reconfigurable robot as well as the CMU Ambler in simulation over arbitrarily complex terrain. A distributed implementation of the planner has also been shown on PolyBot's distributed computational platform.