Collision Detection on Industrial Robots in Repetitive Tasks Using Modified Dynamic Time Warping

Abstract

SUMMARYThis paper presents a non-model-based collision detection algorithm for robots without external sensors and with closed control architecture. A reference signal of repetitive motion is recorded from the robot operation. To detect collisions, the reference is compared with measurements from the robot. One of the key contributions is a novel approach to optimal matching of compared signals, which is ensured by the newly developed modified Dynamic Time Warping (mDTW) method presented in this paper. One of the main improvements of the mDTW is that it enables comparing a signal with the most similar section of the other signal. Partial matching also enables online application of time warping principles and reduces the time and computation resources needed to perform matching. In addition to mDTW, two complementary decision rules are developed to identify collisions. The first rule, based on the absolute difference between compared matched samples, uses statistically determined thresholds to perform rapid detection of unambiguous collisions. The second rule is based on Eigen values of the covariance matrix of matched samples, and it employs its higher sensitivity to detect collisions with lower intensity. Results from experimental validation of the proposed collision algorithm on two industrial robots are shown.

A Framework for Inclusion of Unmodelled Contact Tasks Dynamics in Industrial Robotics

“…In industrial robotics, signals available at the level of robot joint usually include current values, joint angles, and in some cases torques or their estimated values. Previous research and analysis of the available signal properties [ 12 , 13 , 31 ] has observed that the measurements of currents and torque estimations are repeatable for similar movements, but that sampling is often inconsistent due to a lack of true parallel-processing capabilities.…”

“…As a result, they are now offering different Industry 4.0 functionalities, connectivity, and simulation-related options, at least for their new and upcoming products [ 3 ]. Furthermore, related topics that have made undisputedly valuable contributions to novel industrial concepts are: collision detection and avoidance [ 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 ], physical human–robot interaction [ 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 ], kinesthetic guidance [ 19 , 20 , 26 ], motion planning, digital twins, augmented reality, and facilitated programming.…”

“…Solutions based on non-model-based collision detection [ 9 , 12 , 13 , 14 ] intrinsically include the dynamics of the task itself, and their principles do indeed correspond to the requirements for detection and comparison of contact force profiles. However, the relative drawback of this approach is that it is limited to application in repetitive tasks, including identical or very similar motion to the motion during which the reference was recorded.…”

“…The approach proposed in this paper relies on recently developed modifications of the Dynamic Time Warping algorithm [ 13 ] together with algorithms for automatic identification of kinematic parameters of an industrial robot [ 32 , 33 , 34 , 35 , 36 ] to enable a reliable and applicable solution for inclusion of intentional dynamics of a robot’s end effector. Using the robot’s kinematic model, it is possible to determine projection of intentional contact forces onto individual axes of the robot and comparing them with expected values enables distinction between phases of normal operation and erroneous states, including collisions, load manipulation anomalies, and improper alignment.…”

Hierarchical Reinforcement Learning Considering Stochastic Wind Disturbance for Power Line Maintenance Robot

“…The output of the rule-base model and other conventional inputs are provided to the Sugeno fuzzy model, and the effective steering angle is used as the final output to avoid obstacles existing in the environment and safely guide the humanoid robot to the target point. Gordic and Jovanovic et al [6] develops two complementary decision rules to identify conflicts.…”