Grasping strategy for moving object using Net-Structure Proximity Sensor and vision sensor

Abstract

This study presents a robot-hand-arm system with high robustness and responsiveness by using a "Net-Structure Proximity Sensor." The sensor, which we have developed and specially designed for a robot hand, directly detects an object being to be grasped and outputs analog voltage signals according to the position/posture error between the robot hand and the object. It has been confirmed that the robot hand is able to quickly adjust to and grasp an unknown object by applying a feed-back control method based on the sensor signals. This paper focuses on the integration of the proximity-based feedback control to a commonly-used vision-based control. These sensors work in complementary manner: a vision sensor is available for planning an approaching path of a robot hand by detecting large area, and a Net-Structure Proximity Sensor enables the robot hand to adjust the approaching error before grasping and to improve the certainty of the grasping. Two objective velocities are derived independently by the sensors. By adding the velocities with considering the reliability of the sensor information, the robot hand becomes to be able to perform approaching and adjustment to the target object simultaneously. Experimental results showed that the robot hand grasped a moving object with high success rate even in conditions where it was difficult to predict the trajectory of the object accurately.

Integrated control of a multiple-degree-of-freedom hand and arm using a reactive architecture based on high-speed proximity sensing

“…From this result, the integrated control enables high-speed and automatic adjustment of the grasping form and grasping position for uniform reflectance object that is stationary or moving. In particular, the combination of the control and visual-based tracking enabled robot to track a moving object that has random motion (details of combination of the control and visual-based tracking were given in Suzuki et al (2015)). However, it is difficult to track an object that has sharp corners or non-uniform reflectance since the sensor measures reflected light from object surface in a wide range.…”

Iterative path-accurate trajectory generation for fast sensor-based motion of robot arms

“…The constraints are usually ignored, e.g. in [2,3], which is tolerable in the presence of sufficiently small control gains that are computed in a control design aiming at smooth signals. Previous sensor-based control methods of the authors [1,4] used simpler methods for trajectory generation, which is not suitable for fast motion at high sampling rates.…”

“…Assumed limits of the individual axes (before filtering). The units for velocity, acceleration, and jerk are rad/(sampling step), rad/(sampling step) 2 , and rad/(sampling step)3 , respectively. iv iāijij i 1 14 • 10 −3 74 • 10 −6 60 • 10 −6 24 • 10 −6 2 14 • 10 −3 37 • 10 −6 30 • 10 −6 12 • 10 −6 3 14 • 10 −3 85 • 10 −6 69 • 10 −6 28 • 10 −6 4 30 • 10 −3 250 • 10 −6 204 • 10 −6 82 • 10 −6 5 30 • 10 −3 252 • 10 −6 206 • 10 −6 82 • 10 −6 6 56 • 10 −3 450 • 10 −6 368 • 10 −6 147 • 10 −6…”

Reaching, Grasping and Re-grasping: Learning Multimode Grasping Skills

“…In the traditional planning approaches, reaching and grasping are inherently different and usually planned separately and deployed sequentially. For grasping of a moving ball, vision and proximity sensors have been used from a topview [1]. Marturi et al developed an approach of planning pre-grasp posture online and tracking a moving object, where the grasp motion was determined by a human operator [2].…”