Prediction skills can be crucial for the success of tasks where robots have limited time to act or joints actuation power. In such a scenario, a vision system with a fixed, possibly too low, sampling rate could lead to the loss of informative points, slowing down prediction convergence and reducing the accuracy. In this paper, we propose to exploit the low latency, motion-driven sampling, and data compression properties of event cameras to overcome these issues. As a use-case, we use a Panda robotic arm to intercept a ball bouncing on a table. To predict the interception point, we adopt a Stateful LSTM network, a specific LSTM variant without fixed input length, which perfectly suits the event-driven paradigm and the problem at hand, where the length of the trajectory is not defined. We train the network in simulation to speed up the dataset acquisition and then fine-tune the models on real trajectories. Experimental results demonstrate how using a dense spatial sampling (i.e. event cameras) significantly increases the number of intercepted trajectories as compared to a fixed temporal sampling (i.e. frame-based cameras).
翻译:预测技能对于机器人行动或联合激活能力时间有限的任务的成功至关重要。 在这样的假设中,一个具有固定的、可能过低的图像系统,取样率可能导致信息点丢失、预测趋同速度放慢和准确度降低。 在本文中,我们提议利用事件相机的低悬浮度、运动驱动取样和数据压缩特性来克服这些问题。作为一个使用案例,我们使用潘达机器人臂来拦截桌上的球弹跳。为了预测截取点,我们采用了一种状态式LSTM网络,一种没有固定输入长度的LSTM变量,完全适合事件驱动模式和手头问题,轨迹长度没有确定。我们用模拟方式培训网络,以加快数据集的获取,然后在实际轨迹上微调模型。实验结果表明如何使用密度的空间取样(即事件摄像头),与固定的时间取样(即基于框架的照相机)相比,大大增加了截获的轨迹数。</s>