A new castor wheel mechanism for omni-directional mobile platform is presented. A motion of translation is transformed into a rotation to steer the wheel with the help of a helical path fits into a translation joint a...A new castor wheel mechanism for omni-directional mobile platform is presented. A motion of translation is transformed into a rotation to steer the wheel with the help of a helical path fits into a translation joint and three rollers whose axes are connected to the driving shaft of the wheel. When the path moves in translation it acts on the rollers for steering. The path-roller friction transmission, the wheel kinematics and the maneuverability have been analyzed.展开更多
For a domestic personal robot, personalized services are as important as predesigned tasks, because the robot needs to adjust the home state based on the operator's habits. An operator's habits are composed of...For a domestic personal robot, personalized services are as important as predesigned tasks, because the robot needs to adjust the home state based on the operator's habits. An operator's habits are composed of cues, behaviors, and rewards. This article introduces behavioral footprints to describe the operator's behaviors in a house, and applies the inverse reinforcement learning technique to extract the operator's habits, represented by a reward function. We implemented the proposed approach with a mobile robot on indoor temperature adjustment, and compared this approach with a baseline method that recorded all the cues and behaviors of the operator. The result shows that the proposed approach allows the robot to reveal the operator's habits accurately and adjust the environment state accordingly.展开更多
A novel hyper-redundant manipulator named RT1 is designed and studied. The unique feature of RT1 is all degrees of freedom (DOF) are actuated with only one motor via special designed hinge bar universal joints. The me...A novel hyper-redundant manipulator named RT1 is designed and studied. The unique feature of RT1 is all degrees of freedom (DOF) are actuated with only one motor via special designed hinge bar universal joints. The mechanisms of RT1 are introduced in detail. Some experiments are carried out in order to test the movability and adaptability of the manipulator. RT1 is actuated by pulse string and acts discretely. The discrete working space of RT1 is described and the parameter optimization for kinematical redundancy resolution is studied also. The optimization criterion is altering the design parameter as little as possible during manipulator's motion from the initial position to the expected position. An optimization example is given that is realized with Matlab optimize tool-box.展开更多
文摘A new castor wheel mechanism for omni-directional mobile platform is presented. A motion of translation is transformed into a rotation to steer the wheel with the help of a helical path fits into a translation joint and three rollers whose axes are connected to the driving shaft of the wheel. When the path moves in translation it acts on the rollers for steering. The path-roller friction transmission, the wheel kinematics and the maneuverability have been analyzed.
基金supported in part by Hong Kong RGC GRC (CUHK14205914 and CUHK415512)
文摘For a domestic personal robot, personalized services are as important as predesigned tasks, because the robot needs to adjust the home state based on the operator's habits. An operator's habits are composed of cues, behaviors, and rewards. This article introduces behavioral footprints to describe the operator's behaviors in a house, and applies the inverse reinforcement learning technique to extract the operator's habits, represented by a reward function. We implemented the proposed approach with a mobile robot on indoor temperature adjustment, and compared this approach with a baseline method that recorded all the cues and behaviors of the operator. The result shows that the proposed approach allows the robot to reveal the operator's habits accurately and adjust the environment state accordingly.
文摘A novel hyper-redundant manipulator named RT1 is designed and studied. The unique feature of RT1 is all degrees of freedom (DOF) are actuated with only one motor via special designed hinge bar universal joints. The mechanisms of RT1 are introduced in detail. Some experiments are carried out in order to test the movability and adaptability of the manipulator. RT1 is actuated by pulse string and acts discretely. The discrete working space of RT1 is described and the parameter optimization for kinematical redundancy resolution is studied also. The optimization criterion is altering the design parameter as little as possible during manipulator's motion from the initial position to the expected position. An optimization example is given that is realized with Matlab optimize tool-box.
