视觉本体感觉中的低成本机器人潜在表示
Latent Representations for Visual Proprioception in Inexpensive Robots
AI总结：
本文探讨了低成本机器人通过单个外部摄像头图像进行视觉本体感觉的可行性，比较了CNN、VAE、ViT和fiducial标记袋等潜在表示方法的性能。
摘要：
机器人操作需要显式或隐式了解机器人关节位置。精确的本体感觉在高质量工业机器人中是标准配置，但在操作非结构化环境的低成本机器人中往往不可用。本文探讨了在最简单的操作设置中，一个快速的单次回归架构能否通过单个外部摄像头图像实现视觉本体感觉。我们探索了多种潜在表示，包括CNN、VAE、ViT和未校准的fiducial标记袋，并采用适应有限数据的微调技术进行研究。我们通过在低成本6自由度机器人上的实验评估了可实现的准确性。
英文摘要：
Robotic manipulation requires explicit or implicit knowledge of the robot's joint positions. Precise proprioception is standard in high-quality industrial robots but is often unavailable in inexpensive robots operating in unstructured environments. In this paper, we ask: to what extent can a fast, single-pass regression architecture perform visual proprioception from a single external camera image, available even in the simplest manipulation settings? We explore several latent representations, including CNNs, VAEs, ViTs, and bags of uncalibrated fiducial markers, using fine-tuning techniques adapted to the limited data available. We evaluate the achievable accuracy through experiments on an inexpensive 6-DoF robot.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
