Robust grasping in cluttered environments remains an open challenge in robotics. While benchmark datasets have significantly advanced deep learning methods, they mainly focus on simplistic scenes with light occlusion and insufficient diversity, limiting their applicability to practical scenarios. We present GraspClutter6D, a large-scale real-world grasping dataset featuring: (1) 1,000 highly cluttered scenes with dense arrangements (14.1 objects/scene, 62.6% occlusion), (2) comprehensive coverage across 200 objects in 75 environment configurations (bins, shelves, and tables) captured using four RGB-D cameras from multiple viewpoints, and (3) rich annotations including 736 K 6D object poses and 9.3B feasible robotic grasps for 52 K RGB-D images. We benchmark state-of-the-art segmentation, object pose estimation, and grasp detection methods to provide key insights into challenges in cluttered environments. Additionally, we validate the dataset's effectiveness as a training resource, demonstrating that grasping networks trained on GraspClutter6D significantly outperform those trained on existing datasets in both simulation and real-world experiments.

The transition to electric vehicles (EVs) demands lithium-ion batteries (LIBs) customized for diverse energy and power density requirements, yet the intricate trade-offs among electrode design parameters make conventional trial-and-error optimization costly and time-consuming. This study presents the battery electrode exploration network (BattleNet), a deep learning model that predicts the specific capacity across multiple C-rates, collectively representing the rate capability, from electrode design parameters, including loading level, thickness, and porosity. Trained entirely on real-world experimental data, BattleNet achieved an R2 of 0.889, outperforming conventional machine learning baselines. Based on these predictions, an inverse design framework was proposed to explore design parameters satisfying a target rate capability. The explored parameters matched the target with an average error of 7.9%, and cells fabricated within the explored region satisfied the target performance with an average error of merely 4.5%. These results demonstrate the practical feasibility of deep learning as a tool to accelerate LIB design and development for the EV industry.

Recent studies have explored the use of hand-object interaction videos to develop human-like skills for robots. Estimating hand pose and reconstructing the hand mesh is crucial for transferring human motion to robot motion in hand-object interaction videos. However, acquiring hand pose and hand mesh annotations is challenging, which often limits data collection to virtual or controlled laboratory environments. In this study, we propose a source-free domain adaptation method based on pseudo-labeling for hand mesh reconstruction using mask-mesh consistency. First, we construct a hand mesh reconstruction model with two separate heads: a segmentation head and a mesh head. Additionally, we assess the consistency between predictions from the two heads (segmentation masks and reconstructed meshes) to create reliable pseudo labels during adaptation to the target domain. These pseudo labels are then utilized to fine-tune the model for adaptation to the target domain. After applying our approach to the target domain, the model’s performance improves by 5% across all metrics for hand mesh reconstruction.