Integrating large language models (LLMs) for personalized household tidying, achieving 91.2% accuracy on unseen objects.

Jimmy Wu, Rika Antonova, Adam Kan et al.

FMCW mmWave radar enables robust motion estimation and object detection in adverse conditions, outperforming optical sensors in fog and dust environments.

Kyle Harlow, Hyesu Jang, Timothy D. Barfoot et al.

Proposes behavior retrieval using learned similarity metrics to select relevant offline behaviors, boosting robot imitation learning by over 20%.

Maximilian Du, Suraj Nair, Dorsa Sadigh et al.

VRB leverages human videos to learn visual affordances, enabling multi-task robot manipulation via multi-modal contact and trajectory prediction.

Shikhar Bahl, Russell Mendonca, Lili Chen et al.

L3MVN leverages large language models for zero-shot visual navigation, achieving success rates over 76% on Gibson and 50% on HM3D datasets.

Bangguo Yu, Hamidreza Kasaei, Ming Cao

Proposes AMS-DRL for drone navigation in multi-pursuer pursuit-evasion game, achieving over 85% success rate in simulations.

Jiaping Xiao, Mir Feroskhan

Aerostack2 is a ROS2-based multi-UAV autonomous framework supporting platform independence, behavior-driven control, validated in simulation and real flights.

Miguel Fernandez-Cortizas, Martin Molina, Pedro Arias-Perez et al.

ARMBench is a large-scale, object-centric dataset for warehouse robotic manipulation, with 235K+ activities and 190K+ objects, supporting segmentation, recognition, and defect detection.

Chaitanya Mitash, Fan Wang, Shiyang Lu et al.

This study compares asexual/sexual brain reproduction within Darwinian/Lamarckian frameworks, finding asexual+Lamarckian yields best robot performance.

Jie Luo, Carlo Longhi, Agoston E. Eiben

Text2Motion combines LLMs and geometric planning to generate feasible robot action sequences for long-horizon tasks, achieving 82% success rate.

Kevin Lin, Christopher Agia, Toki Migimatsu et al.

AVLMaps fuses audio, visual, and language features into a 3D map, boosting robot multimodal goal navigation by 50%.

Chenguang Huang, Oier Mees, Andy Zeng et al.

This paper introduces LLM-GROP, integrating large language models with task and motion planning to improve multi-object rearrangement success rate by over 20%.

Yan Ding, Xiaohan Zhang, Chris Paxton et al.

ElC-OIS introduces ellipsoidal clustering for LiDAR open-world instance segmentation, achieving 10% improvement in association quality.

Wenbang Deng, Kaihong Huang, Qinghua Yu et al.

FluidLab introduces a fully differentiable physics platform supporting multi-material, multi-coupling fluid manipulation tasks, enabling advanced RL and optimization methods with real-world transfer.

Zhou Xian, Bo Zhu, Zhenjia Xu et al.

ORORA employs GNC-based robust rotation estimation and anisotropic translation modeling, reducing errors by over 20% in noisy radar odometry.

Hyungtae Lim, Kawon Han, Gunhee Shin et al.

Proposes a probabilistic roadmap-based method for contact-rich manipulation, enabling heavy object movement with environmental support, without explicit contact mode analysis.

Kento Nakatsuru, Weiwei Wan, Kensuke Harada

Combining reinforcement learning and sequential optimization, the method achieves up to 150% improvement in intersection management metrics.

Nishchal Hoysal G., Pavankumar Tallapragada

FAEP employs ATSP-based path optimization and adaptive yaw planning, reducing exploration time by over 20% and path length by 20% compared to state-of-the-art methods.

Yinghao Zhao, Li Yan, Hong Xie et al.

Laser-based loop closure integrated into commercial DVL-INS improves underwater map consistency by 30%, using factor graph optimization without raw sensor data.

Thomas Hitchcox, James Richard Forbes

Deep RL with motion primitives enables efficient, robust UAV path planning for active target sensing, outperforming heuristics.

Harsh Goel, Laura Jarin Lipschitz, Saurav Agarwal et al.