ROBORMBENCH reveals reward instability in vision-language models under semantically equivalent instructions, featuring 2,390 trajectories and 21,673 paraphrases.

Wonje Jeung, Sangyeon Yoon, Hyesoo Hong et al.

Using ACT, this study examines visual distractors' impact on imitation policies, significantly improving UR3e robustness.

Vivek Chavan, Pengtao Xie, Yahuan Shi et al.

Proposes a neuro-symbolic framework combining VLA control and task graphs for long-horizon vision-language-action manipulation.

Vivek Chavan, Yahuan Shi, Oliver Heimann et al.

Developed a humanoid robot prototype for multimodal HRI, achieving 96% gesture recognition accuracy.

Thang Tran Viet, Thanh Nguyen Canh, Huy Uong Gia et al.

Behavior Trees lack adaptability in robotic systems, needing enhancements for dynamic environments.

Mehran Rostamnia, Gianluca Filippone, Ricardo Caldas et al.

FIRE-LIVWO achieves robust LiDAR-Inertial-Visual-Wheel Odometry with mmWave radar enhancement, average localization error of 5.677m.

Kun Hu, Menggang Li, Kaidi Wu et al.

RoboSPA evaluates VLA models with 527K trajectories in complex scenes and long-horizon tasks.

Zhenxuan Fan, Bo Zhang, Yutong Lin et al.

H2INT uses a two-stage Transformer to enhance robot navigation safety and robustness in dense crowds.

Ao Shen, Kaixi Chen, Shiwei Liu et al.

Combining VLA model and compliance controller enhances robot-to-human bimanual handover efficiency.

Pasquale Marra, Stefano Berti, Gabriele Mario Caddeo et al.

MulDP employs multimodal diffusion models to enable autonomous quadruped navigation across complex terrains, achieving 89.7% success in diverse scenarios.

Kangmai Hu, Yueqi Zhang, Peng Zhai et al.

Combining semantic segmentation and photogrammetry, the method localizes weld seams with ~4.2mm RMSE using smartphone images.

Augustin Raju, Abilash Madavath, Chandra Yuvesh Aubeeluck et al.

R2S-Eval combines real-to-sim calibration with VLM preference evaluation for stable robot behavior ranking.

Yidi Wang, Feixiang Ruan, Ruoqu Chen et al.

Proposes TRACE framework with 98.6% evidence traceability, enabling end-to-end decision auditability for autonomous robots.

Cagri Temel

SG-AMP combines robust depth completion, scene graph reasoning, and semantics-aware active view planning, achieving 55.27% semantic mIoU and 38.67% PQ on pepper data.

Rohit Menon, Shiva Rudra Lolla, Niklas Mueller-Goldingen et al.

A behavior architecture combining environment templates and behavior trees enables fast, resilient, and adaptable humanoid loco-manipulation with runtime editing.

Duncan Calvert, Luigi Penco, Dexton Anderson et al.

This study compares expert and imitation policies using Transformer-based ACT in ParcelStow, revealing significant success rate decline at higher speeds, with expert maintaining better robustness.

Clinton Enwerem, John S. Baras, Calin Belta

Proposes DroneCATS-Agent using multimodal LLMs for autonomous drone control, covering commanding, approaching, tracking, and multi-drone coordination, evaluated on a unified benchmark.

Jaewoo Park, Minyoung Lee, Sukmin Seo et al.

Extends Rao-Blackwellized online POMDP with hybrid belief representation, reducing sampling variance for high-dimensional robotic planning.

Jiho Lee, Nisar Ahmed, Kyle Hollins Wray et al.

LightNav-0 leverages pretrained VLM's spatial reasoning via unified pointing and RVQ trajectory decoding, enabling multi-task embodied navigation without task-specific heads.

Shaoan Wang, Aocheng Luo, Fei Huang et al.

Zeva enables in-context causal learning, allowing robots to self-evolve without parameter updates, improving success rates over repeated attempts.

Fu Chen, Xin Ding, Bingjia Huang et al.