🤖 AI Summary
Existing approaches for online 3D deformation sensing of soft and continuum robots suffer from either low accuracy and fabrication complexity of embedded sensors, or poor robustness of markerless vision methods—due to reliance on extrinsic camera calibration or prior geometric models. This paper proposes the first end-to-end, real-time 3D deformation estimation method that is markerless, calibration-free, and geometry-agnostic. Given only synchronized stereo RGB images as input, a lightweight CNN directly regresses a parametric shape representation. The method operates at 25 Hz for online deployment. It significantly improves robustness against occlusion, illumination variation, and mounting misalignment. Evaluated on highly deformable platforms—including a robotic manipulator and a biomimetic fish—the approach achieves up to 4.4% higher localization accuracy than state-of-the-art markerless methods, demonstrating strong generalization across diverse morphologies and operating conditions.
📝 Abstract
The precise control of soft and continuum robots requires knowledge of their shape. The shape of these robots has, in contrast to classical rigid robots, infinite degrees of freedom. To partially reconstruct the shape, proprioceptive techniques use built-in sensors resulting in inaccurate results and increased fabrication complexity. Exteroceptive methods so far rely on placing reflective markers on all tracked components and triangulating their position using multiple motion-tracking cameras. Tracking systems are expensive and infeasible for deformable robots interacting with the environment due to marker occlusion and damage. Here, we present a regression approach for 3D shape estimation using a convolutional neural network. The proposed approach takes advantage of data-driven supervised learning and is capable of real-time marker-less shape estimation during inference. Two images of a robotic system are taken simultaneously at 25 Hz from two different perspectives, and are fed to the network, which returns for each pair the parameterized shape. The proposed approach outperforms marker-less state-of-the-art methods by a maximum of 4.4% in estimation accuracy while at the same time being more robust and requiring no prior knowledge of the shape. The approach can be easily implemented due to only requiring two color cameras without depth and not needing an explicit calibration of the extrinsic parameters. Evaluations on two types of soft robotic arms and a soft robotic fish demonstrate our method's accuracy and versatility on highly deformable systems in real-time. The robust performance of the approach against different scene modifications (camera alignment and brightness) suggests its generalizability to a wider range of experimental setups, which will benefit downstream tasks such as robotic grasping and manipulation.
