Pose Estimation of a Cable-Driven Serpentine Manipulator Utilizing Intrinsic Dynamics via Physical Reservoir Computing

2025-09-21

AI Summary

Low pose estimation accuracy in lightweight tendon-driven serpentine manipulators—caused by tendon slack, elongation, and joint deformation—remains a critical challenge. To address this, we propose a novel state-awareness method based on Physical Reservoir Computing (PRC), which treats the system’s inherent nonlinear dynamics not as disturbances but as a high-dimensional temporal feature source. Leveraging the manipulator’s physical structure as a natural computing substrate, our approach enables real-time, physics-informed state reconstruction. The PRC framework is trained exclusively on experimental data, achieving a mean pose estimation error of 4.3 mm—substantially lower than that of analytical models (39.5 mm) and comparable to an LSTM baseline. This work represents the first application of PRC to pose estimation for flexible manipulators, establishing a new, interpretable, and computationally efficient sensing paradigm for soft and tendon-driven robotic systems.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Learning with Manifolds

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Cable-driven serpentine manipulators hold great potential in unstructured environments, offering obstacle avoidance, multi-directional force application, and a lightweight design. By placing all motors and sensors at the base and employing plastic links, we can further reduce the arm's weight. To demonstrate this concept, we developed a 9-degree-of-freedom cable-driven serpentine manipulator with an arm length of 545 mm and a total mass of only 308 g. However, this design introduces flexibility-induced variations, such as cable slack, elongation, and link deformation. These variations result in discrepancies between analytical predictions and actual link positions, making pose estimation more challenging. To address this challenge, we propose a physical reservoir computing based pose estimation method that exploits the manipulator's intrinsic nonlinear dynamics as a high-dimensional reservoir. Experimental results show a mean pose error of 4.3 mm using our method, compared to 4.4 mm with a baseline long short-term memory network and 39.5 mm with an analytical approach. This work provides a new direction for control and perception strategies in lightweight cable-driven serpentine manipulators leveraging their intrinsic dynamics.

Problem

• Estimating pose of lightweight cable-driven manipulators with flexibility-induced variations
• Addressing discrepancies between analytical predictions and actual link positions
• Overcoming challenges from cable slack, elongation, and link deformation

Innovation

• Physical reservoir computing for pose estimation
• Exploiting intrinsic nonlinear dynamics as reservoir
• Achieving low mean pose error of 4.3mm