Skip to content
#Perception and localization
Oct 26Mon
  1. New Strategy Robotics18

    Bluecore Robotics' Five CeMAT Highlights: VR-Teleoperated Humanoid Robot VB2, Chassis H6, and Transport Robot V400

    Bluecore Robotics will showcase five highlights at Booth C3-3, Hall N1, Shanghai New International Expo Centre, from November 3 to 6, 2026, including the VR-headset-teleoperated humanoid robot VB2, the humanoid robot chassis H6, the point-to-point transport robot V400, ultra-thin latent and cage-cart transport robots, and Mayer Vision 3D vision sensors. The V400 targets lightweight short-distance transport, requires no deployment of a scheduling system, and supports rapid deployment in 30 minutes; the ultra-thin latent robot has a body thickness of 120 mm. Visitors can experience the VB2's multimodal perception, task understanding, and precise force control capabilities on site.

  3. 拓斯达50

    In optical workshops, how does Topstar's embodied intelligence cross the "deployment" hurdle?

    Topstar's humanoid dual-arm robot AOI glass wiping workstation has completed validation in the workshops of a leading 3C customer and an optical customer, integrating the functions of two stations—inline AOI inspection and wiping—into a single machine. The workstation has a repeat positioning accuracy of ±0.05mm; it locks onto stain positions via vision and performs wiping with flexible force control, relying on a high-resolution industrial camera and an edge AI computing unit to complete the full chain from image acquisition to defect classification and localization. Ordinary production line workers can quickly get up to speed, reducing training costs and human error and helping improve overall customer workshop yield.

Oct 25Sun
  1. 高工咨询 · 微信公众号52

    Honglu Steel Structure wins repeat order for Henan Mine's nine-axis robotic welding workstation

    Honglu Steel Structure announced on October 23 that it has received another order from Henan Mine for its "nine-axis robotic welding workstation," with the customer adding intelligent welding equipment on top of the first batch of devices. Earlier in September, Honglu Steel Structure also successively won orders for cantilever dual-machine shared-rail, 8-axis and 9-axis cantilever welding workstations, and on October 22 reached a batch procurement cooperation with a steel structure enterprise covering 8 eight-axis inverted cantilever workstations and 10 upright floor-rail workstations.

  2. 机器人产业应用 · 微信公众号72

    DEEP Robotics releases five embodied brain achievements, including DR-WM-1.0

    DEEP Robotics has released five research results built around its self-developed embodied brain, DEEPRobotics-Brain: the world model DR-WM-1.0, the embodied foundation model DR-VLA-2.0, the embodied agent DR-Agent, the policy optimization framework DR-APO, and the data closed-loop platform DR-Benchmark.

  3. 机器人前瞻 · 微信公众号58

    Amap Momentum robot dog Tutu begins inspection duties at Alibaba Xixi Campus

    During the 2026 QinCheng Conference, the Amap Momentum robot dog Tutu took part in guided explanations and tours, and together with Alibaba Group General Affairs and QinCheng Smart, released a smart campus case study and joint solution, bringing Tutu's inspection work at the Hangzhou Xixi Campus into the spotlight. Amap divides the ABot system into three layers—DATA, MODEL, and AGENT—supported by the ABot-N1 navigation base and the ABot-M0.5 manipulation base, and adopts a dual-speed architecture of cloud-based macro planning plus on-device embodied execution.

  4. 优宝特 · 微信公众号18

    Yobotics Robots Debut at Three-Domain Expo, Showcasing Embodied Intelligence Equipment

    Yobotics Robotics showcased multiple self-developed embodied intelligent robots at the Electronics and Artificial Intelligence exhibition area of the Aerospace, Aviation, Maritime and "Two Capabilities" Integration Shandong Collaborative Empowerment Event held in Jinan. The company has established a full technology chain spanning "joint modules—robot bodies—motion control cerebellum—intelligent brain." Its models feature strong obstacle-crossing capability, water- and dust-resistance, and autonomous perception in complex environments, making them suitable for scenarios such as space launch site inspections, aviation equipment maintenance, offshore platforms, and ship cabin interiors. At the event, academicians and experts exchanged views on scenario adaptation and industrial chain support under the special operating conditions of the three domains.

  5. 深蓝AI · 微信公众号81

    TU Delft's MonoRace achieves 100 km/h autonomous drone racing using only a single front-facing camera

    The MonoRace system from TU Delft's MAVLab in the Netherlands, relying only on a single front-facing camera and an IMU, defeated three world-champion-level pilots in a row at the 2025 Abu Dhabi Autonomous Drone Racing competition; the paper was published in Science Robotics on October 14, 2026.

    Why it matters: The Delft team broke down how a monocular camera plus IMU divides perception, state estimation, and reinforcement-learning control in high-speed racing, which can be transferred to real onboard systems with limited compute.

  6. Xbotics具身智能实验室 · 微信公众号42

    DEEP Robotics Tongchui M1 with AgileX PiPER-X Arm Helps NTU Team Win IROS 2026 LRC Fully Autonomous Group Championship and Best Autonomous Capability Award

    At IROS 2026 LRC, a team from Nanyang Technological University, Singapore, used the DEEP Robotics Tongchui M1 quadruped robot with an AgileX Robotics PiPER-X robotic arm mounted on its back (with a depth camera on the end effector), winning the Fully Autonomous Group championship and the Best Autonomous Capability Award. The PiPER-X features a spherical wrist joint design at the end effector, has a payload of 1.5 kg, and can move the camera to adjust viewing distance and angle to complete hazardous chemical label recognition. Through device feedback, coordinate calibration, and task scheduling, the team organized movement, observation, and recognition into a complete autonomous inspection process.

  7. 3D视觉工坊 · 微信公众号71

    HKUST proposes W2-VLA: predicting future wrist latent variables enables 80Hz fine manipulation

    Authors from the Hong Kong University of Science and Technology propose World-to-Wrist VLA (W2-VLA), which uses global task context to predict future wrist latent variables and then guide fine action generation. The method achieves 98.5% average success rate on LIBERO, 60.71% and 18.21% on the Easy/Hard settings of RoboTwin 2.0, respectively, and outperforms baselines under standard and OOD conditions on three real-world tasks: tabletop cleanup, occluded placement, and dual-arm plug insertion.

  8. 3D视觉工坊 · 微信公众号22

    The hotter world models get, the more dangerous SLAM becomes? What robots lack isn't "imagining the future" but "remembering this moment"

    Addressing the problem that world-model predictions may be built on outdated perceptions of the environment, SLAM-MER at CVPR 2026 uses recent keyframe temporal information and a retrievable 3D representation for monocular SLAM, while GaME in the same year continuously updates its 3D Gaussian representation and removes outdated keyframe observations.

Oct 24Sat
  1. 3D视觉工坊 · 微信公众号42

    After feedforward reconstruction becomes 1,200 times faster, is BA still necessary in dynamic 4D reconstruction?

    StreamSplat at ICLR 2026 achieves purely feedforward, online generation of dynamic 3DGS directly from uncalibrated video streams, at 1,200 times the speed of optimization-based methods. But MoRe at CVPR 2026 actively embeds a BA-like refinement module in its purely feedforward pipeline; removing it raises Sintel ATE from 0.147 to 0.155. BA-Track, an ICCV 2025 Oral, uses a 3D point tracker to decompose camera and object motion, adapting classic BA to dynamic scenes.

  2. OFweek Robotics75

    DEEP Robotics and seven universities release five DEEPRobotics-Brain embodied brain results

    DEEP Robotics has released five research results built around its self-developed embodied brain DEEPRobotics-Brain: the world model DR-WM-1.0, the embodied foundation model DR-VLA-2.0, the embodied agent DR-Agent, the policy optimization framework DR-APO, and the data closed-loop platform DR-Benchmark. The company says the work was carried out jointly with seven universities, including MIT, Tsinghua University, and Zhejiang University.

  4. HuggingFace Daily Papers71

    RoboJev-27B: An Open-Source Vision-Language Model for Robot Manipulation Success Detection

    RoboJev-27B is an open-weight vision-language model that takes a task instruction and 10 frames of a manipulation attempt to judge whether the robot completed the task. It achieves 95.2% balanced accuracy and 0.993 AUROC on 268 held-out episodes of the same robot model (SO-101), and an AUROC of 0.890 on 459 episodes from unseen labs and robots. Median inference time is 0.26 seconds per episode on a single H100, and the model, inference code, and evaluation results for 29 model/protocol entries are released together.

Oct 23Fri
  1. arXiv cs.RO60

    EvSLAM: A Benchmark Framework for Event-Camera SLAM in High-Speed Maneuvers

    The authors propose EvSLAM, a benchmark framework for event-camera state estimation that covers multiple data-collection platforms, extreme lighting, and challenging motion patterns, and provides an explicit definition of high-speed maneuvers along with new evaluation metrics. The paper first analyzes the limitations of existing event-camera VO/VIO methods and the shortcomings of public datasets, then uses the framework to evaluate current state-of-the-art methods, summarizing better architectures and problems that remain to be solved.

  2. arXiv cs.RO58

    Relative Localization for Cooperative UAV Formations Using Active Marker Reflections

    This paper proposes a method for onboard relative localization that uses reflections of active markers on specular near-planar surfaces, requiring only a camera, active markers, and a single-beam rangefinder, with no prior knowledge of robot size, marker configuration, or surface reflectance properties. The authors characterize, analytically and experimentally, how surface tilt biases the estimate and identify the slope range over which the level-surface assumption holds. Indoor multi-UAV and outdoor experiments validate the localization accuracy, with higher accuracy than existing vision-based active-marker methods beyond 30 meters.

  4. 深蓝AI · 微信公众号67

    IROS 2026 NIDAR uses RGB for zero-shot LiDAR point cloud intensity generation

    The IROS 2026 paper NIDAR proposes generating pseudo near-infrared images from RGB images and using intrinsic decomposition to add point-level intensity to existing point clouds; after offline training, it can transfer zero-shot to target scenes. In the Warehouse and Hospital sequences in Isaac Sim, after replacing with NIDAR intensity, the ATE RMSE of ISC-LOAM decreased by about 43.0% and 41.1%, respectively, compared with the simulator's built-in intensity.

  5. HuggingFace Daily Papers62

    Ψ-0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model

    The research team proposes Ψ-0.6, a unified vision-language world model that adaptively combines perception, language, geometry, and simulation within a shared reasoning process called streams of thought. These streams alternately generate and interpret images, text, and explicit representations of geometry and motion through a shared token interface. The model surpasses leading open-weight models zero-shot on multi-view spatial reasoning, with further gains from reasoning through geometric intermediate representations.

  6. Robotics & Automation News45

    Infineon announces winners of 2026 humanoid robotics startup challenge, Italy's AdapTronics takes first place

    Infineon announced the winners of its 2026 Startup Challenge. Italian robotics startup AdapTronics took first place with a grasping technology that can pick up a wide variety of objects without traditional suction cups or mechanical grippers; the technology can be applied to humanoid robots, logistics, packaging, and space robotics.

  7. 戴盟机器人55

    Daimon Participates in Drafting National Standard GB/T 48317.2—2026 for Humanoid Robot Environmental Perception, Now Released

    The State Administration for Market Regulation has approved and released GB/T 48317.2—2026, "Technical Requirements for Humanoid Robots — Part 2: Environmental Perception," with Daimon participating in its development as the only embodied-intelligence visuotactile company among the drafting units. This batch of 6 national standards for humanoid robots covers general provisions, environmental perception, decision planning, motion control, task operation, and simulation testing platforms, and will take effect on April 1, 2027. Two other national standards involving Daimon have entered the public comment stage, and "Artificial Intelligence — Embodied Intelligence Intelligence Grading," which Daimon helped compile, has entered the approval stage.

Oct 22Thu
  2. 3D视觉工坊 · 微信公众号29

    Suzhou sandisiwei High-Precision 3D Structured Light Cameras: Support Robotic Arm Grasping, Vision Measurement, Welding, and Outdoor Scenarios

    Suzhou sandisiwei has launched the KW series and SD-M series of 3D structured light cameras, targeting robotic arm grasping, vision measurement, welding, and outdoor scenarios. The KW series is suited to workpiece loading and unloading, depalletizing and palletizing, robot vision guidance, and industrial measurement; the SD-M series supports three modes—area scan, oscillating line scan, and fixed line scan—and focuses on high-precision measurement, welding, and spraying. It includes models such as the SD-M2600, SD-M51000C, and SD-M52000C, and offers an SDK and usage tutorials.

  3. Xbotics具身智能实验室 · 微信公众号72

    TaskAnchor lets VLA use execution history to address task-state confusion in long-horizon manipulation tasks

    TaskAnchor connects execution history to VLA's existing language and vision interfaces through a lightweight adapter, aiming to alleviate task-state confusion in long-horizon manipulation. It uses a dual-path design: a normalized task-state coordinate that describes semantic execution stages, and a visual residual based on context-adaptive test-time training (CA-TTT) that preserves historical details.

  4. 机器人前瞻 · 微信公众号73

    TeleAI and others propose NEXUS, a cross-terrain perception and motion control foundation, enabling Unitree G1 to perform full-body actions on stairs and slopes

    The China Telecom Artificial Intelligence Research Institute (TeleAI), Gamma Intelligence, Shanghai Jiao Tong University, the University of Hong Kong, and Zhejiang University jointly proposed NEXUS, a cross-terrain perception and motion control foundation for humanoid robots that lets robots autonomously adjust posture and contact based on terrain while preserving motion intent.

  5. 机器之心 · 微信公众号73

    RoboColiseum evaluates GPT, Claude, and Gemini robotics capabilities: Claude Opus 5.5 edges ahead, but general models still trail policy models

    Embodied intelligence evaluation platform RoboColiseum released an evaluation report: Claude Opus 5.5 ranked first among four multimodal models with 76.28 points, followed closely by GPT-6 Astra with 75.99 points, while GPT-6.1 Sol and Gemini 4 Argon scored 70.91 and 66.86 points respectively; the top two on the official overall leaderboard remain specialized embodied policy models Paimon (77.54 points) and HiDream-O1-Embodied (76.92 points).

  6. OFweek Robotics53

    Viewtrix showcases shipbuilding and marine engineering intelligent manufacturing solutions at China Marine Economy Expo

    Hunan Viewtrix Robotics Co., Ltd. exhibited a dual-machine collaborative welding workstation, a humanoid welding robot, an intelligent residual-material scanning system, an intelligent grinding workstation, and the KUNWU industrial simulation platform at the 2026 China Marine Economy Expo in Shenzhen.

  7. 36Kr Embodied Intelligence56

    LG Innotek partners with Nvidia to develop physical AI perception solutions

    LG Innotek, part of LG Group, is partnering with Nvidia to jointly develop perception solutions for physical artificial intelligence and robotics. LG Innotek will provide camera modules, lidar, and radar fusion perception technology, while Nvidia will contribute its Holoscan Sensor Bridge platform to enable direct data connections between sensors and GPUs.

  8. arXiv cs.RO56

    TrackDeform3D: A Markerless 3D Keypoint Tracking and Dataset Collection Framework for Deformable Objects Using RGB-D Cameras

    TrackDeform3D is an affordable and autonomous framework for collecting 3D datasets of deformable objects using only RGB-D cameras. It identifies 3D keypoints and robustly tracks their trajectories with motion consistency constraints, producing temporally smooth and geometrically consistent data.

  9. arXiv cs.RO60

    SSIO: A Self-Supervised Inertial Odometry Method Without Ground-Truth Trajectories

    The paper proposes a self-supervised inertial odometry training scheme called SSIO, in which a myopic teacher independently integrates the IMU within each short window to supervise the student model, an approach called integration self-supervision. Although the student is supervised only by short-window velocity changes, it learns to predict velocity directly and does so more accurately than its integration teacher. Pose graph distillation is then used to further refine the model with a cross-window consistency objective.

  11. arXiv cs.RO58

    RoboCap: A six-camera head-mounted platform and Grounded API for egocentric robot learning

    The research team introduces RoboCap, a 250-gram head-mounted device with six cameras and dual IMUs for in-the-wild egocentric data collection, along with the Grounded API, a device-agnostic suite of 3D algorithms. The report shows how the hardware, calibration, and 3D algorithms work together to achieve state-of-the-art performance on public benchmarks, covering SLAM across diverse settings and rigs, egocentric depth estimation, and hand tracking when adapted to third-party devices.

  12. arXiv cs.RO60

    Robot Learning with Visual Predicted Force: Achieving Force-Aware Manipulation Through Visual Force Prediction

    The paper proposes achieving force-aware manipulation by visually predicting the deformation of a compliant Fin Ray gripper, without requiring force or tactile sensors at deployment. The method trains two models: first, a visual force estimator is trained on calibration data to annotate demonstrations with force estimates; second, an action-force proposal policy is trained to jointly generate candidate actions and their corresponding forces. At test time, candidate actions are sampled and the action whose predicted force is closest to a target from the demonstrations is executed. The method was evaluated on four tasks: berry picking, empty-can grasping, in-hand reorientation, and plug insertion.

  13. arXiv cs.RO51

    Action-Conditioned World Model for Robotic Neck Ultrasound Target Plane Guidance

    This study proposes a local action-conditioned world model framework for probe guidance toward target planes in robotic ultrasound, using a two-stage model-based learning pipeline: first, a latent conditional diffusion world model predicts future ultrasound observations from recent context frames, probe motion, and temporal offset; second, a goal-conditioned temporal Transformer predicts ordered probe actions and is fine-tuned using rewards from the frozen world model.

  14. arXiv cs.RO55

    Hilti-Trimble-Oxford dataset released: a benchmark for 360-degree visual-inertial SLAM and floor plan localization

    The paper releases the Hilti-Trimble-Oxford dataset, collected at an active construction site. It contains 30 visual-inertial sequences covering 10 floors over an eight-month span, and captures real-world challenges such as changing lighting, moving workers, fast motion, and repetitive structures. Ground-truth trajectories were collected with a high-precision LiDAR-inertial SLAM system rigidly attached to the 360 camera. The authors also report results from the accompanying open research challenge: 62 teams entered the SLAM track, while only 22 entered floor plan localization, indicating less attention to the latter.

  15. arXiv cs.RO55

    MiTaS multi-resolution tactile imitation learning framework for contact-rich manipulation tasks

    MiTaS is a multi-resolution tactile representation framework that uses modality-specific convolutional stems and a Transformer-based fusion structure to integrate information from an RGB camera, a GelSight Mini vision-based tactile sensor, and a high-frequency event-based Evetac sensor, then conditions a flow-matching policy to perform downstream tasks.

  16. arXiv cs.RO60

    Safe-Night VLA: Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulation

    Safe-Night VLA is a multimodal manipulation framework that integrates long-wave infrared thermal perception into a pre-trained vision-language backbone, enabling robots to perform semantic reasoning based on thermodynamic properties and to enforce deterministic workspace constraints during policy execution through a control barrier functions safety filter.