Research Projects

Follow the CV + Pubs link to view and download my publications.

Evolving Gaits for Improved Active Sensing of Terrain

Limbs are an attractive approach to certain niche robotic applications, such as urban search and rescue, that require both small size and the ability to locomote through highly rubbled terrain. Unfortunately, a large number of degrees of freedom implies there is a large space of non- optimal locomotion trajectories (gaits), making gait adaptation critical. On the other hand, these extra degrees of freedom open many possibilities for active sensing of the terrain, which is essential information for adapting the gait. In previous work, we developed a metric for terrain classification that makes use of the loping body motion (i.e. gait bounce) during locomotion. In this work we developed a framework for evolving gaits to better differentiate the gait bounce signal across terrains. This framework includes a limb/terrain interaction model that estimates gait bounce based on established models of wheel/terrain interaction, and an objective function that can be optimized for terrain discriminability. Additional objective functions for improved locomotion were developed, as well as culling agents that help guide the evolution process away from real-world impossibilities.

Terrain Classification Using Spatio-temporal Characteristics of Visual Motion

In the Collaborative Systems Lab with Dr. Richard Voyles, we developed a new terrain classification technique both for effective, autonomous locomotion over rough, unknown terrains and for the qualitative analysis of terrains for exploration and mapping. Our approach requires a single camera with little processing of visual information. Specifically, we derived a gait bounce measure from visual servoing errors that results from vehicle-terrain interactions during normal locomotion. Characteristics of the terrain, such as roughness and compliance, manifest in the spatial patterns of this signal and can be extracted using pattern classification techniques. This vision-based approach is particularly beneficial for resource-constrained robots with limited sensor capability. With a rigorous study of more than 700 trials, we obtained an 83% accuracy on a set of laboratory terrains. This approach may be used for gait adaptation, particularly with respect to efficiency. We established the viability of this technique on other locomotion mechanisms such as wheels and treads.

Automatic Training Data Selection Through Programming by Human Demonstartion

Programming by demonstration can be implemented with a supervised learning technique such as artificial neural networks (ANN) to learn a sen- sor-motor mapping. Problems exist with such techniques, however, including creating a training set which is compre- hensive (for robustness) and concise (for efficient training). We developed a framework for nonexpert users to collect ~good~ training data from an intuitive understanding of task behavior, not from knowledge of the underlying learning mechanism. However, the training data represents blocks of undesirable behavior due to user error and reposition, as well as desirable behavior. The undesirable behavior is filtered using a characteristic sensor vector that provides a baseline of performance. The approach was successfully utilized to learn wall-following for a wheeled robot using sonar.

LARs : Layered Architecture for Robotics