Visual object recognition is a useful skill for robots to possess. However, present approaches to the problem do not scale to large numbers of objects (few manage more than 10) and require too much computation for real-time tasks on a robot. This paper presents a hybrid decision tree/support vector machine approach to recognition which is fast, with recognition times under one second. A new test dataset is also presented, consisting of over 100,000 images of Lego bricks, acquired by repeatedly dropping the bricks. The proposed method achieves 96% accuracy on the set of 89 different types of Lego bricks, demonstrating its applicability for large-scale real-time visual object recognition.

Cars are becoming, in effect, a robotic system with an embedded human. It is not possible to know what the driver is thinking. We can, however, monitor their gaze and compare it with information in their view-field to make an inference. In this paper we present a complete system that reads speed signs in real-time, compares the driver gaze, and provides immediate feedback if the sign has been missed by the driver. This paper focuses on correlating measures of driver gaze direction with the position of signs in the road scene and improving recognition of signs through image enhancement.

We present a new topological/metric approach to solving the simultaneous localisation and mapping problem. The map is represented as a graph - nodes are local map frames, and edges are transformations between adjacent map frames. The underlying local mapping algorithm is FastSLAM. The local maps and transformations are modelled by sets of particles. There is no global map frame, each map's uncertainties are restricted to its own map frame. The loop dosing is achieved via efficient map matching. We demonstrate our algorithm running in real-time in an indoor environment using a laser range sensor.

This paper presents various optimisation that can be applied to the sum of absolute differences (SAD) correlation algorithm for automated landmark detection. This has applications in mobile robotic navigation and mapping. We show how some assumptions about the environment and the generic form of strong landmarks selected by the SAD correlation algorithm have led to the development of an algorithm to enable near real tune selection of strong landmarks from visual information. The landmarks that have been selected from a series of frames using our optimisation are shown to be stable through the image sequence, demonstration the scale invariance of the landmarks that are selected by the SAD correlation algorithm.

Explores the issues involved in deployment of mobile robots in real-world situations and presents solutions and approaches under development at the Australian National University. For deployment of mobile robots outside of the laboratory, long-term operation is required. Hence, we have developed an automatic recharging system. In addition, a Web-based teleoperation system is used to provide missions to test the long-term reliability of the robot. The final aspect of real-world operation that is explored here is operations in dynamic environments. To date, researchers have assumed static environments for mapping and localisation. We propose methods to avoid this restriction.

Many control applications are by nature distributed, not only over different processes but also over several processors. Managing such a system with respect to the startup of processes, internal communications and state changes quickly becomes a very complex task. The paper presents a distributed control architecture which supports a formal model of computation as described by Lyons and Arib (1989). The architecture is primarily intended for robot control but has a wide range of potential applications. We motivate the design and implementation of the architecture by discussing the desired properties of a robot system capable of doing real-time tasks like manipulation. This leads to functionality such as a process algebra controlling the life-cycle of the processes, grouping and distribution of processes and internal communication transparent to location. Our implementation does not in itself introduce any bottlenecks due to a tree structure with local control over processes which gives an efficient and scalable architecture. At the end, an example scenario in which a fairly advanced problem like opening a door using a mobile robot with a manipulator arm is demonstrated in the presented framework.

A new mobile robot localization technique is presented which uses multiple Gaussian hypotheses to represent the probability distribution of the robot location in the environment. Sensor data is assumed to be provided in the form of a Gaussian distribution over the space of robot poses. A tree of hypotheses is built, representing the possible data association histories for the system. Covariance intersection is used for the fusion of the Gaussians whenever a data association decision is taken. However, such a tree can grow without bound and so rules are introduced for the elimination of the least likely hypotheses from the tree and for the proper re-distribution of their probabilities. This technique is applied to a feature-based mobile robot localization scheme and experimental results are given demonstrating the effectiveness of the scheme.

A discrete event controller synthesis methodology for the successful convergence of assembly tasks is presented. The modelling of an assembly process as a hybrid dynamic system has been shown to be a very effective strategy to incorporate both the continuous and discrete natures of the interaction between the workpiece and its environment. Prior works have presented separate controller synthesis methodologies for both velocity- and force-controlled systems and here we present the next step, a hybrid force/velocity controller. Force control is a natural paradigm for assembly as it is fundamentally compliant and velocity control is used to ensure that frictional forces are overcome during sliding motions. Experimental results for a four degree of freedom assembly task are presented, demonstrating the robustness of the system to very large positioning and orientation errors.

Much attention has been given to CONDENSATION methods for mobile robot localization. This has resulted in somewhat of a breakthrough in representing uncertainty for mobile robots. In this paper we use CONDENSATION with planned sampling as a tool for doing feature based global localization in a large and semi-structured environment. This paper presents a comparison of four different feature types: sonar based triangulation points and point pairs, as well as lines and doors extracted using a laser scanner. We show experimental results that highlight the information content of the different features, and point to fruitful combinations. Accuracy, computation time and the ability to narrow down the search space are among the measures used to compare the features. From the comparison of the features, some general guidelines are drawn for determining good feature types.

We study some modifications of the CONDENSATION algorithm. The case studied is feature based mobile robot localization in a large scale environment. The required sample set size for making the CONDENSATION algorithm converge properly can in many cases require too much computation. To manage with a sample set size which in the normal case would cause the CONDENSATION algorithm to break down. We study two modifications. The first strategy, called "CONDENSATION with random sampling", takes part of the sample set and spreads it randomly over the environment the robot operates in. The second strategy, called "CONDENSATION with planned sampling", places part of the sample set at planned positions based on the detected features. From the experiments we conclude that the second strategy is the best and can reduce the sample set size by at feast a factor of 40.

In this paper, off-the-shelf algorithms for force/torque control are used in the context of mobile manipulation, in particular, the task of opening a door is studied. To make the solution robust, as few assumptions as possible are made. By using relaxation of forces as the basic level of control more complex information can be derived from the resulting motion. In our system, the radius and centre of rotation of the door are estimated online. This enables the complete system to have a higher degree of autonomy in an unknown environment. In addition, the redundancy of the robot is exploited in such a way to drive the system towards a desired configuration. The framework of hybrid dynamic systems is used to implement the algorithm which gives a theoretically sound framework for analysing the system with respect to safety and functionality. The integration of the above approaches results in a system which can robustly locate and grasp the handle and then open the door.

A new, complete discrete event framework for modelling and control of mobile robots is presented. Discrete event modelling is the natural paradigm for systems where motion is constrained by the presence of obstacles. As the mobile robot encounters obstacles the system dynamics change dramatically. These changes are explicitly represented by discrete events. The discrete event framework supports the use of existing path planning techniques as well as reactive approaches and considers the dynamics of the robot. A number of discrete event models for mobile robots have been proposed but these use rather arbitrary definitions for the discrete states. Instead, we rigorously define the discrete state from the currently active constraints upon the robot. Experimental results demonstrating the application of the discrete event model for path planning and control of a nonholonomic mobile robot in indoor office navigation tasks are presented.

A new discrete event controller synthesis methodology for the successful convergence of assembly tasks is presented. The modelling of an assembly process as a hybrid dynamic system has been shown to be a very effective strategy to incorporate both the continuous and discrete natures of the interaction between the workpiece and its environment. Prior works have presented controller synthesis methodologies for velocity-controlled systems (McCarragher and Asada, 1995) and here we follow a similar structure for force-controlled systems. Force control is a natural paradigm for assembly as it is fundamentally compliant. Compliance reduces sensitivity to positioning errors, which, are the most common, source of failure in assembly. A non-trivial example is given which demonstrates the effectiveness of this method.

A new discrete event controller synthesis methodology for the successful convergence of assembly tasks is presented. Discrete event control has been shown to be a very effective strategy to incorporate both the continuous and discrete natures of an assembly task. A discrete event controller synthesis methodology for force-controlled systems is highly desirable because force control is naturally compliant and compliance reduces sensitivity to positioning errors. In this paper we present a number of experimental results for the new controller synthesis method, including a complete assembly task. These experiments demonstrate the effectiveness of the combination of discrete event control and force control for assembly tasks, successfully completing the assembly with positioning errors of up to 50 mm and orientation errors of up to 30/spl deg/.