Fast Perception, Planning, and Execution for a Robotic Butler: Wheeled Humanoid M-Hubo

Abstract

As the aging population grows at a rapid rate, there is an ever growing need for service robot platforms that can provide daily assistance at practical speed with reliable performance. In order to assist with daily tasks such as fetching a beverage, a service robot must be able to perceive its environment and generate corresponding motion trajectories. This becomes a challenging and computationally complex problem when the environment is unknown and thus the path planner must sample numerous trajectories that often are sub-optimal, extending the execution time. To address this issue, we propose a unique strategy of integrating a 3D object detection pipeline with a kinematically optimal manipulation planner to significantly increase speed performance at runtime. In addition, we develop a new robotic butler system for a wheeled humanoid that is capable of fetching requested objects at 24% of the speed a human needs to fulfill the same task. The proposed system was evaluated and demonstrated in a real-world environment setup as well as in public exhibition.

Motion Generation Interface of ROS to PODO Software Framework for Wheeled Humanoid Robot

“…• Seamless API interface of ROS middleware to custom RT PODO framework. This is a significant contribution to our previous work [2] by creating a new method of interface for motion generation. • Evaluation and demonstration of the proposed interface arXiv:2001.00358v1 [cs.RO] 2 Jan 2020 on a wheeled humanoid platform M-Hubo.…”

“…This system requires modifying device drivers, which for the proposed simple embedded Raspberry-Pi system is feasible, but for full-scale humanoid systems with multiple PCs can become burdensome. Our previous work of PODO [2] also operates as a heterogeneous framework but only receives minimal visual data from ROS. Not only was the previous framework limited to one-way communication but it did not support any motion generation requests.…”

A Software Architecture for Service Robots Manipulating Objects in Human Environments

“…AM sends the output to the robot and then the controller in the robot will control the actuators to follow the trajectory. For navigation, we use global and local navigation modes [62], [63] that are in the world and robot's coordinate systems, respectively. For global navigation, we use a 2D simultaneous localization and mapping (SLAM) algorithm to localize the robot and detect obstacles in the environment.…”

“…We use Mobile Hubo (M-Hubo) [62], a wheeled humanoid with three omnidirectional wheels (Figure 11a) to test the entire architecture. The robot is under development so we are able to use the right arm only, which is with 7 DOFs.…”

“…More information about M-Hubo can be found in[62] 4 [69]. show a useful comparative study about available motion planners in OMPL.…”