SLAM algorithm applied to robotics assistance for navigation in unknown environments

Abstract

Background: The combination of robotic tools with assistance technology determines a slightly explored area of applications and advantages for disability or elder people in their daily tasks. Autonomous motorized wheelchair navigation inside an environment, behaviour based control of orthopaedic arms or user's preference learning from a friendly interface are some examples of this new field. In this paper, a Simultaneous Localization and Mapping (SLAM) algorithm is implemented to allow the environmental learning by a mobile robot while its navigation is governed by electromyographic signals. The entire system is part autonomous and part user-decision dependent (semi-autonomous). The environmental learning executed by the SLAM algorithm and the low level behaviour-based reactions of the mobile robot are robotic autonomous tasks, whereas the mobile robot navigation inside an environment is commanded by a Muscle-Computer Interface (MCI).

Methods: In this paper, a sequential Extended Kalman Filter (EKF) feature-based SLAM algorithm is implemented. The features correspond to lines and corners -concave and convex- of the environment. From the SLAM architecture, a global metric map of the environment is derived. The electromyographic signals that command the robot's movements can be adapted to the patient's disabilities. For mobile robot navigation purposes, five commands were obtained from the MCI: turn to the left, turn to the right, stop, start and exit. A kinematic controller to control the mobile robot was implemented. A low level behavior strategy was also implemented to avoid robot's collisions with the environment and moving agents.

Results: The entire system was tested in a population of seven volunteers: three elder, two below-elbow amputees and two young normally limbed patients. The experiments were performed within a closed low dynamic environment. Subjects took an average time of 35 minutes to navigate the environment and to learn how to use the MCI. The SLAM results have shown a consistent reconstruction of the environment. The obtained map was stored inside the Muscle-Computer Interface.

Conclusions: The integration of a highly demanding processing algorithm (SLAM) with a MCI and the communication between both in real time have shown to be consistent and successful. The metric map generated by the mobile robot would allow possible future autonomous navigation without direct control of the user, whose function could be relegated to choose robot destinations. Also, the mobile robot shares the same kinematic model of a motorized wheelchair. This advantage can be exploited for wheelchair autonomous navigation.

Figure 1

General system architecture. It is composed by two main sub-systems. One acquisition and processing of the biological signals and a second sub-system for the robot motion control and intelligence.

Figure 2

Electromyographic signal acquisition I. Four channels of electromyographic signal acquisition. In the Triceps Brachii channel the crosstalk amplitude has the same order of the baseline.

Figure 3

Electromyographic signal acquisition II. Biceps B. contraction and Pronator T contraction are shown in the top and middle panels respectively. The output of the classifier is shown in the bottom panel (S_control).

Figure 4

Mobile robot control system. Mobile robot control system.

Figure 5

Features detection of the environment. Line segment and corner detection by a mobile robot. a) The robot and the detected corner show the covariance ellipse associated to them. b) Detection of line and a corner. Both features, the lines and corners, represent the environment through which the mobile robot navigates. The parameters of both features correspond to the ones shown in Eqs. (8) and (9): ρ is the distance of the line to the origin of the coordinate system and α the angle between the x--axis and a normal to that line; on the other hand, Z_R is the distance of the robot to the corner and Z_β is the angle between the x--axis of the robot and the corner.

Figure 6

SLAM general architecture. Architecture of the EKF-based SLAM algorithm with the parallel map. The parallel map stores the information concerning the beginning and ending points of the walls associated with the detected lines from the environment.

Figure 7

Consistency test of the EKF-SLAM algorithm. Consistency test of the EKF-SLAM algorithm used in this paper. a) Simulated environment (solid black lines) with the desired path (dashed blue lines). b) Map reconstruction of the environment. The yellow points correspond to raw laser data; solid black segments represent walls of the environment; green circles correspond to corners; red crosses are the beginning and ending points associated with the segments and the blue line is the path travelled by the mobile robot. c) The error in the x--coordinate of the mobile robot is bounded by two times its standard deviation. d) The error in the y--coordinate. e) The error in the orientation of the mobile robot.

Figure 8

Muscle signals generated for robot navigation. Muscle signals generated for robot navigation; a) set of pronation/supination movements to control the robot motion; b) motion command controls.

Figure 9

Maps obtained after navigation. Maps obtained after navigation; a) Partial construction of the Institute of Automatics using a mobile robot governed by a MCI with SLAM incorporated on it; b) Closing a loop inside the Institute of Automatics, the robot started from point A and traveled around the environment until reaching point B.

Figure 10

Statistical analysis. Subjective rating of the performance of the system based on a questionnaire filled by the volunteers after the trials. The items evaluate maneuverability, response speed, training time, fatigue and how easy is to use. Maximal score is 5. Vertical bars represent the volunteers that took part in the performance evaluation.