The online 3D packing problem has received increasing attention in recent years due to its practical value. However, the problem itself possesses some peculiar properties, such as sequential decision-making and the la...The online 3D packing problem has received increasing attention in recent years due to its practical value. However, the problem itself possesses some peculiar properties, such as sequential decision-making and the large size of the state space, which have made the use of reinforcement learning with Markov decision processes a popular approach for solving this problem. In this paper, we focus on the problem of high variance in value estimation caused by reward uncertainty in the presence of highly uncertain dynamics. To address this, proposed a solution based on auxiliary tasks and intrinsic rewards for the online 3D bin packing problem, guided by a binary-valued network, to assist the agent in learning the policy within the framework of actor-critic deep reinforcement learning. Specifically, the maintenance of two-valued networks and the utilization of multi-valued network estimates are employed to replace the original value estimates, aiming to provide better guidance for the learning of policy networks. Experimentally, it has been demonstrated that our model can achieve more robust learning and outperform previous works in terms of performance.展开更多
When training a stereo matching network with a single training dataset, the network may overly rely on the learned features of the single training dataset due to differences in the training dataset scenes, resulting i...When training a stereo matching network with a single training dataset, the network may overly rely on the learned features of the single training dataset due to differences in the training dataset scenes, resulting in poor performance on all datasets. Therefore, feature consistency between matched pixels is a key factor in solving the network’s generalization ability. To address this issue, this paper proposed a more widely applicable stereo matching network that introduced whitening loss into the feature extraction module of stereo matching, and significantly improved the applicability of the network model by constraining the variation between salient feature pixels. In addition, this paper used a GRU iterative update module in the disparity update calculation stage, which expanded the model’s receptive field at multiple resolutions, allowing for precise disparity estimation not only in rich texture areas but also in low texture areas. The model was trained only on the Scene Flow large-scale dataset, and the disparity estimation was conducted on mainstream datasets such as Middlebury, KITTI 2015, and ETH3D. Compared with earlier stereo matching algorithms, this method not only achieves more accurate disparity estimation but also has wider applicability and stronger robustness.展开更多
文摘The online 3D packing problem has received increasing attention in recent years due to its practical value. However, the problem itself possesses some peculiar properties, such as sequential decision-making and the large size of the state space, which have made the use of reinforcement learning with Markov decision processes a popular approach for solving this problem. In this paper, we focus on the problem of high variance in value estimation caused by reward uncertainty in the presence of highly uncertain dynamics. To address this, proposed a solution based on auxiliary tasks and intrinsic rewards for the online 3D bin packing problem, guided by a binary-valued network, to assist the agent in learning the policy within the framework of actor-critic deep reinforcement learning. Specifically, the maintenance of two-valued networks and the utilization of multi-valued network estimates are employed to replace the original value estimates, aiming to provide better guidance for the learning of policy networks. Experimentally, it has been demonstrated that our model can achieve more robust learning and outperform previous works in terms of performance.
文摘When training a stereo matching network with a single training dataset, the network may overly rely on the learned features of the single training dataset due to differences in the training dataset scenes, resulting in poor performance on all datasets. Therefore, feature consistency between matched pixels is a key factor in solving the network’s generalization ability. To address this issue, this paper proposed a more widely applicable stereo matching network that introduced whitening loss into the feature extraction module of stereo matching, and significantly improved the applicability of the network model by constraining the variation between salient feature pixels. In addition, this paper used a GRU iterative update module in the disparity update calculation stage, which expanded the model’s receptive field at multiple resolutions, allowing for precise disparity estimation not only in rich texture areas but also in low texture areas. The model was trained only on the Scene Flow large-scale dataset, and the disparity estimation was conducted on mainstream datasets such as Middlebury, KITTI 2015, and ETH3D. Compared with earlier stereo matching algorithms, this method not only achieves more accurate disparity estimation but also has wider applicability and stronger robustness.
