No abstract

SummaryWorking with mobile robots, prior to execute the local planning stage, they must know the environment where they are moving. For that reason the perception and mapping stages must be performed previously. This paper presents a survey in the state of the art in detection and tracking of moving obstacles (DATMO). The aim of what follows is to provide an overview of the most remarkable methods at each field specially in indoor environments where dynamic obstacles can be potentially more dangerous and unpredictable. We are going to show related DATMO methods organized in three approaches: model-free, model-based and grid-based. In addition, a comparison between them and conclusions will be presented.

This paper presents a complete traffic sign recognition system, including the steps of detection, recognition and tracking. The Hough transform is used as detection method from the information extracted in contour images, while the proposed recognition system is based on Support Vector Machines (SVM), and is able to recognize up to one hundred of the main road signs. Besides a novel solution to the problem of discarding detected signs that do not pertain to the host road is proposed, for that purpose vehicle-to-infrastructure (V2I) communication and stereo information is used. This paper presents plenty of tests in real driving conditions, both day and night, in which a high success rate and low number of false negatives and true positives were obtained, and an average runtime of 35 ms, allowing real-time performance.

The goal of this paper is to solve the problem of dynamic obstacle avoidance for a mobile platform by using the stochastic optimal control framework to compute paths that are optimal in terms of safety and energy efficiency under constraints. We propose a three-dimensional extension of the Bayesian Occupancy Filter (BOF) (Coué et al. Int. J. Rob. Res. 2006, 25, 19–30) to deal with the noise in the sensor data, improving the perception stage. We reduce the computational cost of the perception stage by estimating the velocity of each obstacle using optical flow tracking and blob filtering. While several obstacle avoidance systems have been presented in the literature addressing safety and optimality of the robot motion separately, we have applied the approximate inference framework to this problem to combine multiple goals, constraints and priors in a structured way. It is important to remark that the problem involves obstacles that can be moving, therefore classical techniques based on reactive control are not optimal from the point of view of energy consumption. Some experimental results, including comparisons against classical algorithms that highlight the advantages are presented.

Abstract-This paper describes a new approach for improving the estimation of the global position of a vehicle in complex urban environments by means of visual odometry and map fusion. The visual odometry system is based on the compensation of the heterodasticity in the 3D input data using a weighted nonlinear least squares based system. RANdom SAmple Consensus (RANSAC) based on Mahalanobis distance is used for outlier removal. The motion trajectory information is used to keep track of the vehicle position in a digital map during GPS outages. The final goal is the autonomous vehicle outdoor navigation in large-scale environments and the improvement of current vehicle navigation systems based only on standard GPS. This research is oriented to the development of traffic collective systems aiming vehicle-infrastructure cooperation to improve dynamic traffic management. We provide examples of estimated vehicle trajectories and map fusion using the proposed method and discuss the key issues for further improvement.