Good motion data is costly to create. Such an expense often makes the reuse of motion data through transformation and retargetting a more attractive option than creating new motion from scratch. Reuse requires the ability to search automatically and efficiently a growing corpus of motion data, which remains a difficult open problem. We present a method for quickly searching long, unsegmented motion clips for subregions that most closely match a short query clip. Our search algorithm is based on a weighted PCA-based pose representation that allows for flexible and efficient pose-to-pose distance calculations. We present our pose representation and the details of the search algorithm. We evaluate the performance of a prototype search application using both synthetic and captured motion data. Using these results, we propose ways to improve the application's performance. The results inform a discussion of the algorithm's good scalability characteristics.

No abstract

In this paper, we describe the design and development of a network of large unmanned ground vehicles (LUGVs) using lowcost, off-the-shelf technology and building upon experience gained at the 2005 Defense Advanced Research Projects Agency (DARPA) Grand Challenge. Our unique distributed architecture allows robots with different capabilities to interact, facilitates the use of multiple programming languages, and supports location and employment transparency of the interacting software agents. We wrote safety-critical and real-time software in Ada to benefit from the language's precise semantics and timing control, while writing navigation, maneuvering, user interaction, and visualization software in Java for rapid, flexible development.

This paper presents an on-line algorithm that provides accurate heading predictions for Unmanned Ground Vehicles (UGVs). The algorithm uses cross-correlation of SICK laser scans to improve the heading predictions from GPS. It was tested on our Centaur vehicles in outdoor urban environments and verified to provide accurate smooth heading predictions.

No abstract