Tactile recognition of 3D objects remains a challenging task. Compared to 2D shapes, the complex geometry of 3D surfaces requires richer tactile signals, more dexterous actions, and more advanced encoding techniques. In this work, we propose TANDEM3D, a method that applies a co-training framework for exploration and decision making to 3D object recognition with tactile signals. Starting with our previous work, which introduced a co-training paradigm for 2D recognition problems, we introduce a number of advances that enable us to scale up to 3D. TANDEM3D is based on a novel encoder that builds 3D object representation from contact positions and normals using PointNet++. Furthermore, by enabling 6DOF movement, TANDEM3D explores and collects discriminative touch information with high efficiency. Our method is trained entirely in simulation and validated with real-world experiments. Compared to state-of-the-art baselines, TANDEM3D achieves higher accuracy and a lower number of actions in recognizing 3D objects and is also shown to be more robust to different types and amounts of sensor noise. Video is available at https://jxu.ai/tandem3d.
翻译:与 2D 形状相比, 3D 表面的复杂几何学要求更丰富的触动信号、 更细的动作和更先进的编码技术。 在此工作中, 我们提出 TANDD3D 方法, 用于对 3D 对象使用触动信号进行勘探和决策的共同培训框架 。 从我们以前的工作开始, 引入了 2D 识别问题共同培训模式, 我们引入了一些进展, 使我们能够向 3D 扩展。 TANDDE3D 是基于一个新型编码器, 该编码器利用 PpointNet+++ 建立3D 接触位置和正常状态的3D对象代表。 此外, 通过启用 6DOF 运动, TANDDD3D 探索并收集高效率的歧视性触碰信息。 我们的方法在模拟和验证时完全经过现实世界实验。 相比, TANDDEDD3 D 实现更高的精确度, 在识别 3D 对象时采取更少的行动, 也显示对不同类型和数量传感器来说更加可靠。 ALs 。</s>