In this paper,we propose the analytical approach for adaptive decode-and-forward(ADF) relaying vehicle-toinfrastructure(V2I) schemes consisting of ND-symbol burst data transmission based on pilot symbol assisted-chann...
详细信息
In this paper,we propose the analytical approach for adaptive decode-and-forward(ADF) relaying vehicle-toinfrastructure(V2I) schemes consisting of ND-symbol burst data transmission based on pilot symbol assisted-channel estimation(PSA-CE) methods over quasi-static Rayleigh fading *** first,we focus on the error-event at relaying on board equipments(OBEs) for ND-symbol burst data transmission,whereas previous researches considered one data symbol transmission so that they showed the best performance *** considering ND-symbol burst for ADF relaying schemes,we derive an exact bit error rate(BER) expression which can be the performance of practical ***,the practical channel estimation(CE) process is considered by pilot symbols ***,we investigate the effects of both a CE error and an estimated noise variance,which can be obtained by pilot symbol assisted(PSA)-CE methods,on the received signal-to-noise ratio(SNR) and ***,the average BER is derived in approximated closed-form expression for an arbitrary link *** derived analytical approach is verified based on the number of relaying OBEs,pilots,and data *** accuracy is confirmed by comparison with simulation results.
Flat objects with negligible thicknesses like books and disks are challenging to be grasped by the robot because of the width limit of the robot's gripper, especially when they are in cluttered environments. Pre-g...
Flat objects with negligible thicknesses like books and disks are challenging to be grasped by the robot because of the width limit of the robot's gripper, especially when they are in cluttered environments. Pre-grasp manipulation is conducive to rearranging objects on the table and moving the flat objects to the table edge, making them graspable. In this paper, we formulate this task as Parameterized Action Markov Decision Process, and a novel method based on deep reinforcement learning is proposed to address this problem by introducing sliding primitives as actions. A weight-sharing policy network is utilized to predict the sliding primitive's parameters for each object, and a Q-network is adopted to select the acted object among all the candidates on the table. Meanwhile, via integrating a curriculum learning scheme, our method can be scaled to cluttered environments with more objects. In both simulation and real-world experiments, our method surpasses the existing methods and achieves pre-grasp manipulation with higher task success rates and fewer action steps. Without fine-tuning, it can be generalized to novel shapes and household objects with more than 85% success rates in the real world. Videos and supplementary materials are available at https://***/view/pre-grasp-sliding.
Background: systems Medicine is a novel approach to medicine, that is, an interdisciplinary field that considers the human body as a system, composed of multiple parts and of complex relationships at multiple levels, ...
详细信息
暂无评论