A framework for adaptive motion control of autonomous sociable guide robot

Abstract

We present a framework by which the motion of an autonomous mobile guide robot is adaptively controlled. A sociable robot should adapt its speed and path to suit the users' activities, without restricting the user movement. By generating adaptive artificial potential fields for the users and the subgoal separately, and integrating them with the basic potential fields generated from obstacles, our robot can adapt to the users' activities and provide sociable tour-guide services. The robot predicts a user's moving speed and adapts to it to maintain the social distance. Moreover, with the proposed framework, users can deviate from the guided path temporarily and return to the original task afterward. Instead of waiting for the users and taking the risk of losing them, the robot deviates from its original path to follow the users and also prepares for returning to the guiding task. The robot restarts the guiding task at that place, which ensures the least cost to reach the goal. Simulation and experimental results show that our framework can automatically generate suitable motion patterns to control the robot adaptively, making it sociable while providing tour guide services.

Robust 2D Mapping Integrating with 3D Information for the Autonomous Mobile Robot Under Dynamic Environment

“…Motion planning in 3D maps also needs more processing time, and the algorithms are usually complex so that they are not widely used by general service robot developers. However, 2D mapping methods usually cannot reflect the environment sufficiently [14,22,23]. The shapes of objects and the occluded areas are always ignored, which may cause dangers or miss the best route for path planning.…”

A Multi-Behavior Planning Framework for Robot Guide

“…To enhance the adaptivity in path selection, Pandey and Alami [4] planned the trajectory via a multi-variant Gaussian model and switched between different guiding modes for corresponding human behaviors. Nakazawa et al [5] and Zhang et al [6] tackled the path planning problem based on artificial potential field, realizing more natural mode transitions with one unified framework. To improve robot adaptivity in migration velocity, a speed adjustment strategy [2] was proposed based on hierarchical Mixed Observability Markov Decision Process (MOMDP) for high-level decision making.…”

“…We ran 50 independent trials for each scene using our method and the artificial potential field (APF) [6], i.e., 150 trials in total for each method. The result is shown in Table I, Table II, and Table III.…”

“…For the overall guide success rate, our approach managed to guide the human agent to arrive at the destination within time limit in all the trials under every scene set. By comparison, the artificial potential field approach [6], although with considerably high success rate, failed in several cases where the deadlock problem happened and exceeded the time limit.…”

“…Therefore, the guide robots should treat human partners as objectives to serve with socially compliant consideration rather than obstacles to avoid. Navigation algorithms that are adaptive to the users have been pursued in previous work [2], [4]- [6]. However, due to the lack of active instructions such as human-like pointing, it is still prone for human partners to get confused about robots' intention.…”