An efficient automatic solution to the feature-based simultaneous localisation and mapping (SLAM) of mobile robots operating in conditions where a number of competing objectives operate simultaneously is proposed. The formulation quantitatively measures the merit of incoming data with respect to multiple priorities, automatically adjusting the amount of observations to be used in the estimation process for the best possible combined outcome. The methodology enables a selection mechanism which can efficiently exploit the observations available to the robot to best fulfil the objectives of differing tasks throughout the course of a mission, e.g. localisation, mapping, exploration, feature distribution, searching for specific objects or victims, etc. The work is particularly motivated by navigation in three-dimensional terrains, and an example considering the objectives of robot localisation and map expansion in a search and rescue environment using an RGB-D camera is utilised for discussion and results.

This paper presents a novel solution for building three-dimensional dense maps in unknown and unstructured environment with reduced computational costs. This is achieved by giving the robot the ‘intelligence’ to select, out of the steadily collected data, the maximally informative observations to be used in the estimation of the robot location and its surroundings. We show that, although the actual evaluation of information gain for each frame introduces an additional computational cost, the overall efficiency is significantly increased by keeping the matrix compact. The noticeable advantage of this strategy is that the continuously gathered data is not heuristically segmented prior to be input to the filter. Quite the opposite, the scheme lends itself to be statistically optimal and is capable of handling large data sets collected at realistic sampling rates. The strategy is generic to any 3D feature-based simultaneous localization and mapping (SLAM) algorithm in the information form, but in the work presented here it is closely coupled to a proposed novel appearance-based sensory package. It consists of a conventional camera and a range imager, which provide range, bearing and elevation inputs to visual salient features as commonly used by three-dimensional point-based SLAM, but it is also particularly well adapted for lightweight mobile platforms such as those commonly employed for Urban Search and Rescue (USAR), chosen here to demonstrate the excellences of the proposed strategy.

This paper presents a novel vision-based sensory package and an information-efficient simultaneous localization and mapping (SLAM) algorithm. Together, we offer a solution for building 3-D dense map in an unknown and unstructured environment with minimal computational costs. The sensory package we adopt consists of a conventional camera and a range imager, which provide range and bearing and elevation inputs as commonly used by 3-D feature-based SLAM. In addition, we propose an algorithm to give the robots the `intelligencerdquo to select, out of the steadily collected data, the maximally informative observations to be used in the estimation process. We show that, although the actual evaluation of information gain for each frame introduces an additional computational cost, the overall efficiency is significantly increased by keeping the matrix compact. The noticeable advantage of this strategy is that the continuously gathered data are not heuristically segmented prior to being input to the filter. Quite the opposite, the scheme lends itself to be statistically optimal and is capable of handling large datasets collected at realistic sampling rates.

The main contribution of this paper is a novel stereo-based algorithm which serves as a tool to examine the viability of stereo vision solutions to the simultaneous localisation and mapping (SLAM) for large indoor environments. Using features extracted from the scale invariant feature transform (SIFT) and depth maps from a small vision system (SVS) stereo head, an extended Kalman filter (EKF) based SLAM algorithm, that allows the independent use of information relating to depth and bearing, is developed. By means of a map pruning strategy for managing the computational cost, it is demonstrated that statistically consistent location estimates can be generated for a small (6 m times 6 m) structured office environment, and in a robotics search and rescue arena of similar size. It is shown that in a larger office environment, the proposed algorithm generates location estimates which are topologically correct, but statistically inconsistent. A discussion on the possible reasons for the inconsistency is presented. The paper highlights that, despite recent advances, building accurate geometric maps of large environments with vision only sensing is still a challenging task

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.