10 October 2022 in IEEE Robotics and Automation Letters
In this letter, we tackle the problem of active robotic 3D reconstruction of an object. In particular, we study how a mobile robot with an arm-held camera can select a favorable number of views to recover an object's 3D shape efficiently. Contrary to the existing solution to this problem, we leverage the popular neural radiance fields-based object representation, which has recently shown impressive results for various computer vision tasks. However, it is not straightforward to directly reason about an object's explicit 3D geometric details using such a representation, making the next-best-view selection problem for dense 3D reconstruction challenging. This paper introduces a ray-based volumetric uncertainty estimator, which computes the entropy of the weight distribution of the color samples along each ray of the object's implicit neural representation. We show that it is possible to infer the uncertainty of the underlying 3D geometry given a novel view with the proposed estimator. We then present a next-best-view selection policy guided by the ray-based volumetric uncertainty in neural radiance fields-based representations. Encouraging experimental results on synthetic and real-world data suggest that the approach presented in this paper can enable a new research direction of using an implicit 3D object representation for the next-best-view problem in robot vision applications, distinguishing our approach from the existing approaches that rely on explicit 3D geometric modeling.
1 January 2019 in Complexity
Shape memory alloy‐ (SMA‐) based actuators are widely applied in the compliant actuating systems. However, the measured data of the SMA‐based compliant actuating system reveal the input‐output hysteresis behavior, and the actuating precision of the compliant actuating system could be degraded by such hysteresis nonlinearities. To characterize such nonlinearities in the SMA‐based compliant actuator precisely, a Jiles‐Atherton model is adopted in this paper, and a modified particle swarm optimization (MPSO) algorithm is proposed to identify the parameters in the Jiles‐Atherton model, which is a combination of several differential nonlinear equations. Compared with the basic PSO identification algorithm, the designed MPSO algorithm can reduce the local optimum problem so that the Jiles‐Atherton model with the identified parameters can show good agreements with the measured experimental data. The good capture ability of the proposed identification algorithm is also examined through the comparisons with Jiles‐Atherton model using the basic PSO identification algorithm.