Search results

Reports on a seminar entitled ‘‘Future trends in robotics'' organised by the UK's Institution of Mechanical Engineers, outlines recent developments in subsea robotics, reviews the evolution of surgical robotics, discusses the current state of application and research relating to mobile robots and looks at the progress being made in the development of climbing robots.

Robot learning ‐ be it unsupervised, supervised or self‐supervised ‐ is one method of dealing with noisy, inconsistent, or contradictory data that has proven useful in mobile robotics. In all but the simplest cases of robot learning, raw sensor data cannot be used directly as input to the learning process. Instead, some “meaningful” preprocessing has to be applied to the raw data, before the learning controller can use the sensory perceptions as input. In this paper, two instances of supervised and unsupervised robot learning experiments, using vision input are presented. The vision sensor signal preprocessing necessary to achieve successful learning is also discussed.

In this paper the problem of the dynamic optimal time‐energy Off‐Line programming of an autonomous mobile robot in a crowded environment is considered. First, kinematic model and planning are presented. Then a dynamic model based on Euler‐Lagrange formalism is developed and a mobility estimation function of the robot is considered. This dynamic estimation of the robot mobility takes into account of the velocity and the orientation of the robot. Then the scene structuration and a path finder algorithm are developed. After, the optimal dynamic off‐line programming is formulated as a nonlinear programming problem under nonlinear equality and inequality constraints. The Discrete Augmented Lagrangian (DAL) is used to obtain the optimal trajectograhy. We develop an extended DAL to DALAP, DALAdaptive Penalty. RoboSim 1.0 simulator is developed to perform kinematic and DALAP based algorithms on a large class of mobile robots optimal time‐energy off‐line programming. A comparative study with kinematic planning is considered. It is shown that the performance of the dynamic optimal time‐energy control and off‐line programming is much better than kinematic and heuristic based schemes. This strategy of trajectory planning was implemented on the case study of the SARA mobile robot model.