Camera-based monitoring system for mobile robot guidance

Abstract

The more the robot knows about its environment, the more eficiently it can operate. This is the basic idea of the system presented in this paper: B y employing an external camera-based sensing system, a global model of the robot's environment is maintained and updated continuously. Thus, motion planning and collision avoidance in a dynamic environment (i.e. an environment which contains moving obstacles) can be done eficiently. For many indoor applications this concept is inherently superior compared to mobile robots which act completely autonomously. The paper presents concepts and components of an experimental system: Sensing is done with CCD cameras; the processed data is furnished to different modules regarding robot localization, obstacle detection and motion planning.

An Optical External Localization System and Applications to Indoor Tracking

“…The system advances the state of the art by achieving accuracy levels in the submillimeter range which has not been achieved by any of the commercial localization systems currently available [3][4][5][6][7]. Specifically, experiments in localization have demonstrated the system to have accuracy levels of 0.18 mm, 0.10 mm and 0.34 mm in the x, y and z coordinate directions respectively.…”

“…Accurate mounting of beacons is required for accurate positioning. Other solutions currently available include: i) electromagnetic sensors (for e.g., MotionStar magnetic tracker [4]) whose accuracy degrades considerably in metallic environments, ii) computer vision techniques [6] (for e.g., systems using networks of 3D cameras such as Microsoft's Easy Living system [4]) which are expensive, complex and require large amounts of processing power and memory and iii) Metris's expensive iGPS system [7] (minimum cost of deployment is around $180,000) which uses multiple infrared lasers and a photosensitive receiver for tracking but suffers for multipath reflections degrading its accuracy substantially below 1mm in small environments (receiver closer the 2m from the transmitter).…”

Intelligent Space as a Platform for Human Observation

“…This means that mobile robots can move along a safe path, but since the generated path doesn't reflect the human motion, robot's movement may interfere with humans'. To the contrary, by avoiding the regions which have a high probability of the presence of people, a path which minimizes the expected travel time (sum of the travel time and the time needed for passing a person on the way) or probability of encountering people was generated in (Kruse & Wahl, 1998). However the authors utilized the observation result of the past and didn't take into account the current positions of people.…”

Feature-Based Prediction of Trajectories for Socially Compliant Navigation

“…Many approaches rather rely on reactive collision avoidance methods [3,25,22]. Other methods evaluate trajectories based on the risk of motion conflicts, given predictions about potential future places covered by people [2,16,29]. Although such methods effectively avoid collisions with humans, the resulting trajectories are often suboptimal with respect to the expectations of the humans due to awkward and unexpected evasive movements.…”