For autonomous robotics applications, it is crucial that robots are able to accurately measure their potential state and perceive their environment, including other agents within it (e.g., cobots interacting with humans). The redundancy of these measurements is important, as it allows for planning and execution of recovery protocols in the event of sensor failure or external disturbances. Visual estimation can provide this redundancy through the use of low-cost sensors and server as a standalone source of proprioception when no encoder-based sensing is available. Therefore, we estimate the configuration of the robot jointly with its pose, which provides a complete spatial understanding of the observed robot. We present GISR - a method for deep configuration and robot-to-camera pose estimation that prioritizes real-time execution. GISR is comprised of two modules: (i) a geometric initialization module, efficiently computing an approximate robot pose and configuration, and (ii) an iterative silhouette-based refinement module that refines the initial solution in only a few iterations. We evaluate our method on a publicly available dataset and show that GISR performs competitively with existing state-of-the-art approaches, while being significantly faster compared to existing methods of the same class. Our code is available at https://github.com/iwhitey/GISR-robot.

翻译：在自主机器人应用中，机器人需具备精确测量自身潜在状态、感知环境（包括环境中其他主体，如与人交互的协作机器人）的能力，这对实际应用至关重要。这类测量的冗余性非常重要，因为它能在传感器故障或外部干扰发生时，支持恢复协议的规划与执行。视觉估计可通过低成本传感器提供这种冗余，并能在无编码器传感的场景下作为本体感知的独立来源。因此，本文联合估计机器人的构型及其位姿，从而实现对观测机器人完整空间信息的理解。我们提出GISR——一种面向实时执行需求的深度构型与机器人-相机位姿估计方法。GISR由两个模块构成：（i）几何初始化模块，高效计算近似的机器人位姿与构型；（ii）基于轮廓的迭代精细化模块，通过少量迭代即可优化初始解。我们在公开数据集上评估该方法，结果表明GISR在保持与现有最先进方法竞争性能的同时，其执行速度显著快于同类现有方法。代码已开源发布于https://github.com/iwhitey/GISR-robot。