23 August 2024 in IEEE Transactions on Industrial Informatics
High DoF mobile manipulation of robots is a nonlinear, nonchain redundant problem. In this article, we focus on two subissues of robot mobile manipulation: whole-body inverse kinematics (whole-body IK) and operation-oriented motion planning (OOMP). Whole-body IK solves the robot arm joint configuration and the mobile base position configuration according to the target pose. OOMP generates a feasible trajectory from the current pose to the target pose. The trajectory can avoid obstacles and touch operated objects. We introduce neural network optimization (NNO) methods with two variations to solve whole-body IK and OOMP, respectively. For whole-body IK, we design a fully connected network (FCN) to predict ten DoF of position and joint configurations based on the target pose. We use these ten DoF configurations to derive the predicted pose for online optimization. For OOMP, we design a GRU-based network to generate trajectories based on the initial and goal states. We mainly adopt sphere masks to modify the point cloud properties of the target object dynamically. During optimization, the trajectory keeps away from point clouds but approaches sphere masks. Finally, we conduct extensive experiments both on a Franka Panda robot and a mobile dual-arm robot. The results demonstrate the superior performance of our NNO method on whole body IK and OOMP, and implement mobile manipulation in different environments successfully.
1 March 2023 in Physics of Fluids
Inferring cryogenic cavitation features from the boundary conditions (BCs) remains a challenge due to the nonlinear thermal effects. This paper aims to build a fast model for cryogenic cavitation prediction from the BCs. Different from the traditional numerical solvers and conventional physics-informed neural networks (PINNs), the approach can realize near real-time inference as the BCs change without a recalculating or retraining process. The model is based on the fusion of simple theories and neural network. It utilizes theories such as the B-factor theory to construct a physical module, quickly inferring hidden physical features from the BCs. These features represent the local and global cavitation intensity and thermal effect, which are treated as functions of location x. Then a neural operator builds the mapping between these features and target functions (local pressure coefficient or temperature depression). The model is trained and validated based on the experimental measurements by Hord for liquid nitrogen and hydrogen. Effects of the physical module and training dataset size are investigated in terms of prediction errors. It's validated that the model can learn hidden knowledge from a small amount of experimental data and has considerable accuracies for new BCs and locations. Besides, preliminary studies show that it has the potential for cavitation prediction in unseen cryogenic liquids or over new geometries without retraining. The work highlights the potential of merging simple physical models and neural networks together for cryogenic cavitation prediction.
1 August 2024 in Review of Scientific Instruments
Efficient thermal management is essential for low-temperature optoelectronic devices. Traditional liquid nitrogen (LN2) cooling presents challenges such as frequent replenishment needs and limited operational duration. This study introduces micromachined Joule–Thomson (MJT) cooling as a superior alternative for temperature regulation in optoelectronic devices. We evaluated the thermal and optical performance of MJT cooling for a CdSe/ZnS quantum dot (QD) sample within a temperature range of 120–300 K. Thermal analysis showed that with a single 50 l nitrogen refill, the MJT system can operate continuously for over one week, surpassing the LN2 system by 11 times. The temperature stability was affected little by laser irradiation, with a <0.2 K rise at 5 mW of laser power. In addition, the MJT cooling led to an average blueshift of 1–3 meV in the emission peak of QDs and 0.3–2.3 meV reduced spectral broadening compared to LN2, attributed to a smaller sample-to-cold-stage temperature gap of about 8–9 K in the MJT setup. The standard deviations of peak energy and FWHM are in the order of E − 1 meV magnitude, demonstrating a comparable thermal uniformity compared to LN2. The vibration spectra obtained for both vertical and horizontal directions reveal the superior low-vibration characteristics of MJT cooling. These findings validate MJT cooling as a superior and reliable strategy for the thermal management of optoelectronics, ensuring prolonged operational durations, reliable temperature stability, enhanced temperature precision, high thermal homogeneity, and low vibrations.