NeuPAN directly maps raw point clouds to latent distance features for real-time, map-free robot navigation using end-to-end model-based learning.

Ruihua Han, Shuai Wang, Shuaijun Wang et al.

Enhanced robotic manipulation data collection via compositional generalization, achieving a 77.5% success rate.

Jensen Gao, Annie Xie, Ted Xiao et al.

mmPlace transforms intermediate frequency signals into range-azimuth heatmaps, employs rotation-based concatenation, achieving 87.37% recall@1 in challenging scenarios.

Chengzhen Meng, Yifan Duan, Chenming He et al.

RL-based H2O enables real-time humanoid teleoperation via RGB camera, achieving dynamic motion imitation with success rate over 72.5%.

Tairan He, Zhengyi Luo, Wenli Xiao et al.

Tac-Man leverages tactile feedback for prior-free manipulation of articulated objects, achieving over 98% success in complex scenarios.

Zihang Zhao, Yuyang Li, Wanlin Li et al.

Proposed a coarse-to-fine affordance learning method to significantly reduce the impact of point cloud noise.

Suhan Ling, Yian Wang, Shiguang Wu et al.

Proposed a multimodal handover failure detection dataset using video, force-torque, and gripper data; baseline methods include 3D CNN and action segmentation, achieving 67.9% accuracy.

Santosh Thoduka, Nico Hochgeschwender, Juergen Gall et al.

Star-Searcher employs hierarchical path planning and viewpoint clustering, reducing path length by 15%, search time by 20%, achieving 100% target completeness.

Yiming Luo, Zixuan Zhuang, Neng Pan et al.

RoboEXP employs an action-conditioned scene graph (ACSG) via interactive exploration, integrating multimodal data for complex scene understanding.

Hanxiao Jiang, Binghao Huang, Ruihai Wu et al.

LIMP translates complex natural language instructions into temporal logic, enabling robots to verify behaviors without prebuilt semantic maps, achieving 79% success in real-world tests.

Benedict Quartey, Eric Rosen, Stefanie Tellex et al.

Proposes StableLego, a force-balance optimization method, accurately predicting the stability of 3D block structures with over 99% accuracy on large datasets.

Ruixuan Liu, Kangle Deng, Ziwei Wang et al.

UMI framework enables direct skill transfer from human demonstrations to robot policies with a 70% success rate.

Cheng Chi, Zhenjia Xu, Chuer Pan et al.

Introduced THE COLOSSEUM benchmark, evaluating 5 manipulation models across 14 environmental perturbations, with success rates dropping 30-50%, over 75% in combined perturbations.

Wilbert Pumacay, Ishika Singh, Jiafei Duan et al.

PIVOT uses iterative visual prompting to enable zero-shot spatial reasoning and robotic control with VLMs, achieving 75% success in navigation tasks.

Soroush Nasiriany, Fei Xia, Wenhao Yu et al.

By conducting semi-structured interviews and observations with 23 guide dog handlers and 5 trainers, this study identifies key interaction challenges and design principles for guide dog robots.

Hochul Hwang, Hee-Tae Jung, Nicholas A Giudice et al.

ALOHA 2 introduces low-cost hardware with improved responsiveness, ergonomics, and robustness, enabling large-scale bimanual teleoperation data collection.

ALOHA 2 Team, Jorge Aldaco, Travis Armstrong et al.

Proposes a deep RL method with dynamic graphs for adaptive path planning in unknown 3D environments, boosting target discovery by 15%.

Apoorva Vashisth, Julius Rückin, Federico Magistri et al.

PoCo leverages diffusion models for probabilistic multi-modal, multi-task policy composition, boosting generalization in robotics.

Lirui Wang, Jialiang Zhao, Yilun Du et al.

SERL uses RLPD with off-policy deep RL, achieving policies in 25-50 min with over 90% success, outperforming state-of-the-art.

Jianlan Luo, Zheyuan Hu, Charles Xu et al.

NeuralFeels integrates vision and touch, online learning neural fields for real-time unknown object pose and shape reconstruction, enhancing robotic in-hand perception.

Sudharshan Suresh, Haozhi Qi, Tingfan Wu et al.