Existing model-based collision detection methods rely on accurate torque dynamic parameters identified using measured joint torques. However, for robots lacking joint torque sensors, only joint currents can be measured, and joint torques must be estimated through the linear relationship between joint currents and joint torque constants. This way can lead to cumulative identification errors in torque dynamic parameters, thereby diminishing the performance of model-based collision detection algorithms. To tackle this challenge, this article proposes an innovative collision detection method based on current residuals, which represent the disparities between measured joint currents and predicted joint currents computed by current dynamic parameters. Then, a dynamic threshold method for current residuals is designed to mitigate the impact of modeling errors at zero-speed direction changes on collision detection performance. Additionally, a suppression strategy based on online load identification and compensation is introduced to reduce the interference of non-collision load factors on collision detection signals. The proposed method mitigates the accumulation of errors on torque dynamic identification resulting from inaccuracies in joint torque constants, ultimately enhancing collision detection performance for robots without joint torque sensors. Extensive experiment results validate the correctness and effectiveness of this approach.

中文翻译：

---

一种基于电流残差的无关节扭矩传感器机器人碰撞检测新方法——以UR10机器人为例

现有的基于模型的碰撞检测方法依赖于使用测量的关节扭矩识别的精确扭矩动态参数。然而，对于缺乏关节扭矩传感器的机器人，只能测量关节电流，并且必须通过关节电流和关节扭矩常数之间的线性关系来估计关节扭矩。这种方式会导致扭矩动态参数的累积识别误差，从而降低基于模型的碰撞检测算法的性能。为了应对这一挑战，本文提出了一种基于当前残差的创新碰撞检测方法，该方法表示测量的关节电流与由当前动态参数计算的预测关节电流之间的差异。然后，设计了一种电流残差的动态阈值方法，以减轻零速方向变化时建模误差对碰撞检测性能的影响。此外，引入基于在线负载识别和补偿的抑制策略，以减少非碰撞负载因素对碰撞检测信号的干扰。所提出的方法减轻了由于关节扭矩常数不准确而导致的扭矩动态识别误差的累积，最终提高了没有关节扭矩传感器的机器人的碰撞检测性能。大量的实验结果验证了该方法的正确性和有效性。