Advances in sensing technology and algorithm design make it possible for a robot equipped with a laser range-finder to generate a map and localise itself within the map as the robot explores its environment.We describe a system for mapping and virtual reconstruction developed as part of a robot for urban search and rescue. The process of mapping and, at the same time, localising the robot within the map, is called Simultaneous Localisation and Mapping (SLAM). In many applications, such as urban search and rescue, information from wheel encoders is inaccurate and cannot be used for odometry to obtain a position estimate. However, iterative closest point scan matching algorithms make it possible for a robot to perform accurate positioning in unstructured environments where wheel slip is common. When this positioning is combined with a mapping algorithm such as FastSLAM, the robot can construct an accurate map in real-time as it moves. Given the generated map and the robot's position within it, a variety of exploration algorithms allow the robot to autonomously explore its environment. The robot is also equipped with an RGB-D camera. The 3D information as well as the colour video images are incorporated into the map to produce a 3D virtual reconstruction of the environment as the robot explores. This robot won the award for best autonomous robot in three successive RoboCup Rescue Robot competitions [1], 2009 - 2011.

Robots are used for Urban Search and Rescue to assist rescue workers. To enable the robots to find victims, they are equipped with various sensors including thermal, video and depth time-of-flight cameras, and laser range-finders. We present a method to enable a robot to perform this task autonomously. Thermal features are detected using a dynamic temperature threshold. By aligning the thermal and time-offlight camera images, the thermal features are projected into 3D space. Edge detection on laser data is used to locate holes within the environment, which are then spatially correlated to the thermal features. A decision tree uses the correlated features to direct the autonomous policy to explore the environment and locate victims. The method was evaluated in the 2010 RoboCup Rescue Real Robots Competition.

The primary purpose of rescue robots is to locate victims within a disaster environment, either to report their position or to deliver aid. Although there exist several solutions for mapping and localizing a robot in an unknown environment, they often require an estimate of the robot's motion. In a disaster site, a robot might not have effective motion encoders, either because of the discontinuous nature of the terrain or because the robot's locomotion devices do not remain in constant contact with the ground. We have developed an algorithm for tracking the position of a robot in a disaster environment and generating a map that functions in real time. Our solution is based on a range finder device and is robust to temporary errors in the range scan. By aligning each scan to an occupancy grid of prior scan data, we can find the robot's position more accurately than current techniques that align only to the previous scan. The accurate position tracking allows us to more efficiently implement a solution to the mapping problem. In addition, our solution can track the position of the robot and generate a map based on three-dimensional scan data, instead of requiring that the range sensor be fixed in a level plane. (C) 2011 Wiley Periodicals, Inc.

Many applications for robotics require that the robot know its current position in the environment. While there exist several solutions for localizing a robot, even in a previously unknown environment, they often require an estimate of the robot's motion. However, in many situations, a robot may not have motion encoders, or its encoders may be highly inaccurate. We have developed an algorithm for tracking the position of a robot, based on a rangefinder device, that is robust to temporary errors in the range scan. By aligning each scan to an occupancy grid of prior scan data, we can find the robot's position more accurately than current techniques which only align to the previous scan. In addition, our solution can track the position of the robot based on three dimensional scan data, instead of requiring that the range sensor be fixed in a level plane.

Tactile sensing is essential for eective manipulation. A detailed understanding of the surface texture can also be used for industrial tasks such as quality assurance. This paper describes an application of machine learning in tactile sensing. A naive Bayes classier is used to distinguish textures sensed by bio-inspired articial nger. The nger has randomly distributed strain gauges and Polyvinylidene Fluoride (PVDF) lms embedded in silicone. The data from the nger are preprocessed and the Fourier coecients of the sensor outputs are used to learn a classier for dierent textures. The nger is capable of distinguishing natural textures but in this paper we describe experiments on articial textures, which we use to calibrate the learner.

In this paper we focus on the development of a device for ambulatory gait monitoring in the home. This belt worn device is designed to function reliably in the home environment, operate at a very low power to facilitate long term usage and be simple to use. The device measures acceleration in three orthogonal directions and can be used to identify motor sensory deficits that could lead to falls in the elderly. The instrument can be used as an emergency or falls monitor or for detecting subtle changes in motor control arising from the effects of prescription drugs or degenerative aging processes. With piezo-resistive accelerometers it is possible to detect both dynamic and static acceleration and the tilt angle relative to the horizontal. This permits the recording of activity, posture, mobility and the ability to identify unexpected loss of motor function as evidenced by stumbles or near falls. The sum of the absolute values of the three orthogonal forces has also been shown to correlate well with energy expenditure. The device is supplied with an alarm button, which when manually activated communicates with the home base station and enables a telephone connection to one of three pre-programmed telephone numbers. These may be dedicated 24-hour call services, other carers or relatives. We describe a clinical scenario using the ambulatory gait monitor and hypothesise that it has benefit in identifying falls, objectively characterising gait and mobility patterns and in assessing treatment progress.

Search and rescue robots are intended to work as aids to human rescuers. One of the research challenges is how to combine autonomous operation with operator control. This paper presents a single software system which independently operates several physically distinct robots. One operator can coordinate several robots by switching their individual mode between autonomous and remote operation. For simple regions, a robot may travel autonomously, while in more complex areas the operator may assert control. The mixture of autonomous and remote operation also allows the robot to continue to operate when wireless communication to the operator is lost.