The goal of this work is to develop a new autonomous capability for remotely deploying precisely located sensor nodes without damaging the sensor nodes in the process. Over the course of the last decade there has been significant interest in research to deploy sensor networks. This research is driven by the fact that the costs associated with installing sensor networks can be very high. In order to rapidly deploy sensor networks consisting of large numbers of sensor nodes, alternative techniques must be developed to place the sensor nodes in the field.

The goal of this work is to develop a new autonomous capability for remotely deploying precisely located sensor nodes without damaging the sensor nodes in the process. Over the course of the last decade there has been significant interest in research to deploy sensor networks. This research is driven by the fact that the costs associated with installing sensor networks can be very high. In order to rapidly deploy sensor networks consisting of large numbers of sensor nodes, alternative techniques must be developed to place the sensor nodes in the field.

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 present 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 are presented, as well as culling agents that help guide the evolution process away from real-world impossibilities.

For controlling robots in an urban search and rescue (USAR) application, a wearable joystick is presented with improved sensing capability as well as a giant magneto-resistance (GMR) sensor model for use with rare-earth magnets. Scientists have been studying a variety of existing human/robot interface devices to control USAR robots in a disaster. Due to the stresses involved in USAR environments, the selection of an appropriate interface device out of the numerous interactive devices available has to be carefully considered. Furthermore, the total burden to the user of human/robot interface devices in USAR tasks includes not only the periods of interaction, but also the burden of transporting and remotely setting up the devices. The wearable joystick presented is developed with the design goal of minimizing total encumbrances. The features of this wearable joystick include easy and wire-free installation into regular gloves. An improved hardware structure for the sensor pad and the alignment of magnets is described that completely wraps the wrist. This band-type mechanism provides more robust data acquisition than previous prototypes. To evaluate performance, time-to-complete tests are performed, with a comparison to a metric for path tortuosity. The fractal dimension of the resulting path is analyzed to represent the degree of control the user has over the interface device. Experimental results are provided from both computer screen tess and real USAR robot driving tests.

We present a new terrain classification technique both for effective, autonomous locomotion over natural, unknown terrains and for the qualitative analysis of terrains for exploration and mapping. Our straight-forward approach requires a single camera with little processing of visual information. Specifically, we derived a gait bounce measure from visual servoing errors that result from vehicle-terrain interactions during normal locomotion. Characteristics of the terrain, such as roughness and compliance, manifest themselves in the spatial patterns of this signal and can be extracted using pattern classification techniques. For legged robots, different limb-terrain interactions generate gait bounce signals with different information content, thus deliberate limb motions can effect higher information content (i.e. the robot is an active sensor of terrain class). Segmentation of the gait cycle based on the limb-terrain interaction isolates portions of the gait bounce signal with high information content. The decoding of, then sequencing of, this content from each cycle segment yields a robust classification of terrain type from known benchmarks. To extract this spatio-temporal pattern of the gait bounce signal, we developed a meta-classifier using discriminant analysis and hidden Markov model. We present the gait bounce derivation. We demonstrate the viability of terrain classification for legged vehicles using gait bounce with a rigorous study of more than 700 trials, obtaining 84% accuracy. We describe how terrain classification can be used for gait adaptation, particularly in relation to an efficiency metric. We also demonstrate that our technique is generally applicable to other locomotion mechanisms such as wheels and treads.

We have investigated the performance of simultaneously estimating the 3D motion and structure for navigation when the scale information is obtained by utilizing the cooperative efforts of multiple robots. The method determines the relative positions of robots by tracking a specific geometric feature that is part of their structure, and then uses the extended Kalman filter to estimate the motion and structure. For implementation we used two CRAWLER Scouts, and performed several experiments to explore the effects of cooperative running of robots on the motion estimation.

A custom version of the TerminatorBot is described for core bored inspection during search-and-rescue operations. "Core bored inspection" refers to visual inspection of a void by passing a small camera through an access hole into the void. This is the classic "camera-on-a-stick" approach. Sometimes the access hole occurs naturally. Sometimes a suspected void has no access hole. To gain access, a hole is bored through the rubble with a coring tool, hence the term "core-bored inspection". In either case, the camera, once inside, can articulate to look around, but is limited to fine-of-sight. Occlusions can prevent a thorough inspection or force using/boring another hole. A small, agile robotic device could augment the use of such cameras. We propose the TerminatorBot as a prototype limbed robot for studying such applications.

Sequencing sensorimotor primitives to achieve complex behaviors can simplify programming of robotic systems. Using programming by demonstration to code the component primitives can further simplify the process. Learning methods employed in programming by demonstration require comprehensive data sets, which place a significant burden on the user during demonstration. We present a generalized method whereby training sets can be automatically filtered, freeing the user from knowledge of the underlying learning method. We achieve this by first capturing the characteristic behavior for a demonstrated task, then determining a measure of distance from that behavior. With this information, data sets can be analyzed to determine whether a particular moment of demonstration is "good" and should be included in the final training set. Results from programming by demonstration of left wall-following on a mobile platform are presented. Additionally, we present a method for on-line performance analysis that takes advantage of the characteristic behavior identified in the filtering process.

We present a method to evaluate the performance of an eigenvector learned sensorimotor primitive for mobile robots. At runtime, the learning system projects sensor data onto the eigenspace using eigenvectors determined in training. The result of the projection is a set of sensor values and actuator values. We developed an error metric based on comparing the projected values with the actual sensor values. When the system performs closely to how it was trained, the difference between projected and actual sensors is small and hence the error metric is small. The error increases as the performance degrades. This method is not task specific and can be used for any eigenvector learned primitive. Two example applications of the error metric are shown using wall following skills for a mobile robot. First, the metric is used as a transition cue for multiprimitive sequential tasks. Second, the error metric is used to create an adaptive system that chooses the best performing skill.

A novel, centimeter-scale crawling robot has been developed to address applications in surveillance, search-and-rescue, and planetary exploration. This places constraints on size and durability that minimizes the mechanism. As a result, a dual-use design employing two arms for both manipulation and locomotion was conceived. In a complementary fashion, this paper investigates the dual-use of visual servoing error. Visual servoing can be used by a mobile robot for homing and tracking. But because ground-based mobile robots are inherently planar, the control methodology (steering) is one-dimensional. The two-dimensional nature of image-based servoing leaves additional information content to be used in other contexts. We explore this information in the context of classifying terrain conditions. An outline for gait adaptation based on this is suggested for future work.