Ngai Ming Kwok

Active vision in robotic systems: A survey of recent developments

In this paper we provide a broad survey of developments in active vision in robotic applications over the last 15 years. With increasing demand for robotic automation, research in this area has received much attention. Among the many factors that can be attributed to a high-performance robotic system, the planned sensing or acquisition of perceptions on the operating environment is a crucial component. The aim of sensor planning is to determine the pose and settings of vision sensors for undertaking a vision-based task that usually requires obtaining multiple views of the object to be manipulated. Planning for robot vision is a complex problem for an active system due to its sensing uncertainty and environmental uncertainty. This paper describes such problems arising from many applications, e.g. object recognition and modeling, site reconstruction and inspection, surveillance, tracking and search, as well as robotic manipulation and assembly, localization and mapping, navigation and exploration. A bundle of solutions and methods have been proposed to solve these problems in the past. They are summarized in this review while enabling readers to easily refer solution methods for practical applications. Representative contributions, their evaluations, analyses, and future research trends are also addressed in an abstract level.

A Comprehensive Performance Evaluation of 3D Local Feature Descriptors

A number of 3D local feature descriptors have been proposed in the literature. It is however, unclear which descriptors are more appropriate for a particular application. A good descriptor should be descriptive, compact, and robust to a set of nuisances. This paper compares ten popular local feature descriptors in the contexts of 3D object recognition, 3D shape retrieval, and 3D modeling. We first evaluate the descriptiveness of these descriptors on eight popular datasets which were acquired using different techniques. We then analyze their compactness using the recall of feature matching per each float value in the descriptor. We also test the robustness of the selected descriptors with respect to support radius variations, Gaussian noise, shot noise, varying mesh resolution, distance to the mesh boundary, keypoint localization error, occlusion, clutter, and dataset size. Moreover, we present the performance results of these descriptors when combined with different 3D keypoint detection methods. We finally analyze the computational efficiency for generating each descriptor.

Game Theory for Wireless Sensor Networks: A Survey

Game theory (GT) is a mathematical method that describes the phenomenon of conflict and cooperation between intelligent rational decision-makers. In particular, the theory has been proven very useful in the design of wireless sensor networks (WSNs). This article surveys the recent developments and findings of GT, its applications in WSNs, and provides the community a general view of this vibrant research area. We first introduce the typical formulation of GT in the WSN application domain. The roles of GT are described that include routing protocol design, topology control, power control and energy saving, packet forwarding, data collection, spectrum allocation, bandwidth allocation, quality of service control, coverage optimization, WSN security, and other sensor management tasks. Then, three variations of game theory are described, namely, the cooperative, non-cooperative, and repeated schemes. Finally, existing problems and future trends are identified for researchers and engineers in the field.

An efficient multiple hypothesis filter for bearing-only SLAM

This paper presents a multiple hypothesis approach to solve the simultaneous localisation and mapping (SLAM) problem with a bearing-only sensor. The main contribution of the paper is to provide a remedy for the landmark initialisation problem that occurs due to the absence of range information, in a computationally efficient manner. Each landmark is initialised in the form of multiple hypotheses distributed along the direction of the bearing measurement. Using subsequent measurements, the validity of the hypotheses is evaluated based on the sequential probability ratio test (SPRT). Consequently, the best approximation to the landmark location is maintained. This approach enables an extended Kalman filler (EKF) to be used for bearing-only SLAM providing a computational efficient solution. Simulation and experimental results, from using a camera as the bearing-only sensor mounted on a Pioneer robot are included to demonstrate the effectiveness of the proposed technique.

Bearing-only SLAM Using a SPRT Based Gaussian Sum Filter

Use of a Gaussian Sum filter (GSF) to efficiently solve the initialisation problem in bearing-only simultaneous localisation and mapping (SLAM) is the main contribution of this paper. When information about the range is not available, the initial probability density function (pdf) of a landmark in the environment can not be represented using a Gaussian. The GSF is an attractive candidate for estimation in this scenario as it can deal with arbitrary pdfs represented as sets of Gaussians. However, the implementation of the GSF requires maintaining a bank of extended Kalman filters. The resulting computational complexity needs to be reduced by employing a minimum number of filters. In this work, the performance of each extended Kalman filter (EKF) in the GSF is evaluated using the sequential probability ratio test (SPRT). As such the number of members in the Gaussian sum can be reduced rapidly and the efficiency of the GSF can be significantly increased, providing a solution to the important problem of bearing-only SLAM. The effectiveness of the proposed approach is demonstrated by simulation and experiment conducted using a Pioneer mobile robot.

Evolutionary particle filter: re-sampling from the genetic algorithm perspective

The sample impoverishment problem in particle filters is investigated from the perspective of genetic algorithms. The contribution of this paper is in the proposal of a hybrid technique to mitigate sample impoverishment such that the number of particles required and hence the computation complexities are reduced. Studies are conducted through the use of Chebyshev inequality for the number of particles required. The relationship between the number of particles and the time for impoverishment is examined by considering the takeover phenomena as found in genetic algorithms. It is revealed that the sample impoverishment problem is caused by the resampling scheme in implementing the particle filter with a finite number of particles. The use of uniform or roulette-wheel sampling also contributes to the problem. Crossover operators from genetic algorithms are adopted to tackle the finite particle problem by re-defining or re-supplying impoverished particles during filter iterations. Effectiveness of the proposed approach is demonstrated by simulations for a monobot simultaneous localization and mapping application.

Emulating self-reconfigurable robots - design of the SMORES system

Self-reconfigurable robots are capable of changing their shape to suit a task. The design of one system called SMORES (Self-assembling MOdular Robot for Extreme Shape-shifting) is introduced. This system is capable of rearranging its modules in all three classes of reconfiguration; lattice style, chain style and mobile reconfiguration. This system is capable of emulating many of the other existing systems and promises to be a step towards a universal modular robot.

Contrast Enhancement and Intensity Preservation for Gray-Level Images Using Multiobjective Particle Swarm Optimization

The contrast enhancement of gray-level digital images is considered in this paper. In particular, the mean image intensity is preserved while the contrast is enhanced. This provides better viewing consistence and effectiveness. The contrast enhancement is achieved by maximizing the information content carried in the image via a continuous intensity transform function. The preservation of image intensity is obtained by applying gamma-correction on the images. Since there is always a trade-off between the requirements for the enhancement of contrast and preservation of intensity, an improved multiobjective particle swarm optimization procedure is proposed to resolve this contradiction, making use of its flexible algorithmic structure. The effectiveness of the proposed approach is illustrated by a number of images including the benchmarks and an image sequence captured from a mobile robot in an indoor environment.

Planning under uncertainty using model predictive control for information gathering

Abstract This paper considers trajectory planning problems for autonomous robots in information gathering tasks. The objective of the planning is to maximize the information gathered within a finite time horizon. It is assumed that either the Extended Kalman Filter (EKF) or the Extended Information Filter (EIF) is applied to estimate the features of interest and the information gathered is expressed by the covariance matrix or information matrix. It is shown that the planning process can be formulated as an optimal control problem for a nonlinear control system with a gradually identified model. This naturally leads to the Model Predictive Control (MPC) planning strategy, which uses the updated knowledge about the model to solve a finite horizon optimal control problem at each time step and only executes the first control action. The proposed MPC framework is demonstrated through solutions to two challenging information gathering tasks: (1) Simultaneous planning, localization, and map building (SPLAM) and (2) Multi-robot Geolocation. It is shown that MPC can effectively deal with dynamic constraints, multiple robots/features and a range of objective functions.

Evolutionary computing based mobile robot localization

Evolutionary computing techniques, including genetic algorithms (GA), particle swarm optimization (PSO) and ants system (AS) are applied to the localization problem of a mobile robot. Salient features of robot localization are that the system is partially dynamic and information for fitness evaluation is incomplete and corrupted by noise. In this research, variations to the above three evolutionary computing techniques are proposed to tackle the specific dynamic and noisy system. Their performances are compared based on simulation and experiment results and the feasibility of the proposed approach to mobile robot localization is demonstrated.