Many robots utilize commercial force/torque sensors to identify inertial properties of unknown objects. However, such sensors can be difficult to apply to small-sized robots due to their weight, size, and cost. In this paper, we propose a learning-based approach for estimating the mass and center of mass (COM) of unknown objects without using force/torque sensors at the end-effector or on the joints. In our method, a robot arm carries an unknown object as it moves through multiple discrete configurations. Measurements are collected when the robot reaches each discrete configuration and stops. A neural network is designed to estimate joint torques from encoder discrepancies. Given multiple samples, we derive the closed-form relation between joint torques and the object's inertial properties. Based on the derivation, the mass and COM of object are identified by weighted least squares. In order to improve the accuracy of inferred inertial properties, an attention model is designed to generate weights of joints, which indicate the relative importance for each joint. Our framework requires only encoder measurements without using any force/torque sensors, but still maintains accurate estimation capability. The proposed approach has been demonstrated on a 4 degree of freedom (DOF) robot arm.
翻译:许多机器人利用商业力量/传感器来识别未知物体的惯性特性。然而,由于重量、大小和成本,这类传感器可能难以适用于小型机器人,因为其重量、大小和成本,因此很难适用于小型机器人。在本文件中,我们建议采用基于学习的方法,在不使用终端效应或关节上使用终端效应或关节上的强制/托克传感器的情况下,估计未知物体的质量质量和质量中心(COM),不使用终端效应或关节点上的强制/托克传感器来估计未知物体的质量质量和质量中心(COM)。在我们的方法中,机器人臂臂携带一个未知物体通过多个离心配置和停止移动时,将采集一个未知物体的未知物体。当机器人到达每个离心配置和停止时,将采集测量测量。设计一个神经神经网络,用来估计相近的神经网络是用来估计联号的联结点。鉴于多个样本,我们从联合点和物体的惯性特性中得出了封闭式关系,而不用使用任何强制/托克传感器,但是仍然保持准确的估算能力。根据衍生的结果,物体的重量是最小的方;为了提高惯性,为了生成的惯性,而设计的注意模型模型,目的是,以产生联合的重量的重量的重量,表明。</s>