Search for: All records

Robotic technology can benefit disassembly operations by reducing human operators’ workload and assisting them with handling hazardous materials. Safety consideration and predicting human movement is a priority in human-robot close collaboration. The point-by-point forecasting of human hand motion which forecasts one point at each time does not provide enough information on human movement due to errors between the actual movement and predicted value. This study provides a range of possible hand movements to enhance safety. It applies three machine learning techniques including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Bayesian Neural Network (BNN) combined with Bagging and Monte Carlo Dropout (MCD), namely LSTM-Bagging, GRU-Bagging, and BNN-MCD to predict the possible movement range. The study uses an Inertial Measurement Units (IMU) dataset collected from the disassembly of desktop computers to show the application of the proposed method. The findings reveal that BNN-MCD outperforms other models in forecasting the range of possible hand movement. 

Abstract Disassembly is an essential step for remanufacturing end-of-life (EOL) products. Optimization of disassembly sequences and the utilization of robotic technology could alleviate the labor-intensive nature of dismantling operations. This study proposes an optimization framework for disassembly sequence planning under uncertainty considering human–robot collaboration. The proposed framework combines three attributes: disassembly cost, safety, and complexity of disassembly, namely disassembleability, to identify the optimal disassembly path and allocate operations between human and robot. A multi-attribute utility function is used to address uncertainty and make a tradeoff among multiple attributes. The disassembly time reflects the cost of disassembly which is assumed to be an uncertain parameter with a Beta distribution; the disassembleability evaluates the feasibility of conducting operations by robot; finally, the safety index ensures the protection of human workers in the work environment. An example of dismantling a desktop computer is used to show the application. The model identifies the optimal disassembly sequence with less disassembly cost, high disassembleability, and increased safety index while allocating disassembly operations among human and robot. A sensitivity analysis is conducted to show the model's performance when changing the disassembly cost for the robot. 

A bstract We present the first complete next-to-leading-order (NLO) prediction with full jet algorithm implementation for the single inclusive jet production in pA collisions at forward rapidities within the color glass condensate (CGC) effective theory. Our prediction is fully differential over the final state physical kinematics, which allows the implementation of any infra-red safe observable including the jet clustering procedure. The NLO calculation is organized with the aid of the observable originated power counting proposed in [1] which gives rise to the novel soft contributions in the CGC factorization. We achieve the fully-differential calculation by constructing suitable subtraction terms to handle the singularities in the real corrections. The subtraction contributions can be exactly integrated analytically. We present the NLO cross section with the jets constructed using the anti- k T algorithm. The NLO calculation demonstrates explicitly the validity of the CGC factorization in jet production. Furthermore, as a byproduct of the subtraction method, we also derive the fully analytic cross section for the forward jet production in the small- R limit. We show that in the small- R approximation, the forward jet cross section can be factorized into a semi-hard cross section that produces a parton and the semi-inclusive jet functions (siJFs). We argue that this feature holds for generic jet production and jet substructure observables in the CGC framework. Last, we show numerical analyses of the derived formula to validate our calculations. We justify when the small- R approximation is appropriate. Like forward hadron production, the obtained NLO result also exhibits the negativity of the cross section in the large jet transverse regime, which signals the need for the threshold resummation. A sketch of the threshold resummation in the CGC framework is presented based on the multiple emission picture and it is found to agree with the approach using the rapidity renormalization group equation developed in [2].