Abstract
Conference Title: 2018 IEEE/ACS 15th International Conference on Computer Systems and Applications (AICCSA) Conference Start Date: 2018, Oct. 28 Conference End Date: 2018, Nov. 1 Conference Location: Aqaba, Jordan Simultaneous Localization and Mapping (SLAM) is a vital task for autonomous robots moving in unknown environments. It is a rigorous and complex problem where the signals of different modalities originating from sensors as diverse as laser range finders, IR sensors, ultrasonic transducers, odometers and inertial measurement units are used in its different variants. Expensive sensory arrangements and significant computational resources are desired in all the variants of SLAM and multi-processing hardware-software arrangements are essentially needed. Consequently, the overall system becomes quite elaborate and expensive. Another common issue is the odometry error; this error accumulates over time and the robot looses track completely or distorts the map. Generally, a notebook computer is used as the computational resource; as it is frequently placed and removed from the robot, the odometry information is significantly affected. Therefore, it is desired to do the sensor calibration with fixed and complete system hardware. In this work, a testbed development for SLAM is reported. In this design, a low-cost and light-weight FPGA SoC development board is used as the main platform along with a low-cost LIDAR sensor; both fixed on the robot and controlled wirelessly. This fixes the whole hardware configuration and hence the weight of the robot, therefore the calibration results do not alter over time. Moreover, a HW-SW co-design approach is adopted to achieve a highly capable but very compact computational resource. Post-processing of the sensory data with rigorous calibration models has resulted in reasonably precise robot's odometry and environmental perception. The complete system is tested in indoor environment and satisfactory localization and mapping results are achieved.