Hydra-Nav: Object Navigation via Adaptive Dual-Process Reasoning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Peking University（北京大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
While large vision-language models (VLMs) show promise for object goal navigation, current methods still struggle with low success rates and inefficient localization of unseen objects--failures primarily attributed to weak temporal-spatial reasoning. Meanwhile, recent attempts to inject reasoning into VLM-based agents improve success rates but incur substantial computational overhead. To address both the ineffectiveness and inefficiency of existing approaches, we introduce Hydra-Nav, a unified VLM architecture that adaptively switches between a deliberative slow system for analyzing exploration history and formulating high-level plans, and a reactive fast system for efficient execution. We train Hydra-Nav through a three-stage curriculum: (i) spatial-action alignment to strengthen trajectory planning, (ii) memory-reasoning integration to enhance temporal-spatial reasoning over long-horizon exploration, and (iii) iterative rejection fine-tuning to enable selective reasoning at critical decision points. Extensive experiments demonstrate that Hydra-Nav achieves state-of-the-art performance on the HM3D, MP3D, and OVON benchmarks, outperforming the second-best methods by 11.1%, 17.4%, and 21.2%, respectively. Furthermore, we introduce SOT (Success weighted by Operation Time), a new metric to measure search efficiency across VLMs with varying reasoning intensity. Results show that adaptive reasoning significantly enhances search efficiency over fixed-frequency baselines.
PM-Nav: Priori-Map Guided Embodied Navigation in Functional Buildings
Faculty of Robot Science and Engineering at Northeastern University（东北大学机器人科学与工程学院）；Foshan Graduate School of Innovation at Northeastern University（东北大学佛山创新研究生学院）；School of Aeronautic Science and Engineering at Beihang University（北航航空科学与工程学院）
NavTuner: Learning a Scene-Sensitive Family of Navigation Policies
College of Computing, Georgia Institute of Technology（佐治亚理工学院计算学院）；Institute for Robotics and Intelligent Machines, Georgia Institute of Technology（佐治亚理工学院机器人与智能机器研究所）
LERR-Nav: Learning to Coordinate Exploration, Recovery, and Reminiscing for Object Navigation
Hong Kong Polytechnic University（香港理工大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；DeepRobotics（深度机器人公司）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Guangzhou University（广州大学）
Enhanced UAV Navigation Systems through Sensor Fusion with Trident Quaternions
Facultad de Ingeniería, Universidad de Buenos Aires（布宜诺斯艾利斯大学工程学院）；Universidad de San Andrés and CONICET（圣安德烈斯大学和CONICET）；Centro de Automática y Robótica (CAR, UPM-CSIC)（自动化与机器人中心（CAR，UPM-CSIC））
NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models
AIML, University of Adelaide（阿德莱德大学AIML）；Adobe Research（奥多比研究院）；University of North Carolina, Chapel Hill（北卡罗来纳大学教堂山分校）；University of California, Santa Cruz（加利福尼亚大学圣克鲁兹分校）
