Skip to content
Only Research#Perception and localization
  1. OFweek Robotics77

    Apple unveils HALO humanoid robot control system; Unitree G1 achieves 91% task success rate in unfamiliar environments

    Apple's research team published the paper "Perceptive Humanoid Motion from Simulation" on arXiv, unveiling HALO, an autonomous humanoid robot control system, and validating it on the Unitree G1.

    Why it matters: Apple's HALO splits task orchestration, motion generation, and tracking into three layers, and reports comparative results of 91% in unfamiliar environments and 70% on composite tasks, offering a look at its layered design and data synthesis pipeline.

  1. 未来机器人网 · 微信公众号77

    D-Robotics and University of Tokyo release RawVLA: frozen VLA, only imaging front end trained, low-light dual-arm task success rate rises from 0 to 66.5%

    D-Robotics, together with the University of Tokyo and other institutions, released the RawVLA technical approach, which adds a learnable neural ISP module before the VLA policy while keeping the VLA model frozen, using action error to train the imaging front end in reverse. On real robots, four dual-arm tasks were tested with π0.5; the average success rate in low light rose from 0% with the default ISP to 66.5%, versus 75.0% in normal light, where the default ISP achieved 76.5%.

    Why it matters: The approach brings the imaging front end into the learnable pipeline and provides comparative data under low light and normal light, offering a reference for vision pipeline design.

  1. 3D视觉工坊 · 微信公众号78

    Any3R goes open source: one model unifies 3D reconstruction and pose estimation for pinhole, fisheye, and panoramic cameras

    South Dakota State University and other institutions propose Any3R, which uses a dense ray field to describe arbitrary central cameras, reconstructing a 3D point cloud and estimating pose from mixed-camera images in a single forward pass. The method replaces the row and column indices of rotary position encoding with angular coordinates and weights the pixel loss by solid angle, so one set of weights covers pinhole, fisheye beyond 180°, and 360° panoramic cameras. On benchmarks spanning 13 central camera types and 3 datasets, it leads in both reconstruction accuracy and pose accuracy; the inference code, 13 camera models, and weights are open-sourced.

    Why it matters: The article presents a feed-forward 3D reconstruction method that replaces the pinhole assumption with a dense ray field, offering insight into handling mixed inputs from multiple camera types.

  1. 甲子光年 · 微信公众号78

    Peking University's Dong Hao team proposes One Scan is Enough: embodied navigation post-training with a single scan

    Dong Hao's team at Peking University has published the paper "One Scan is Enough," which uses a LiDAR-equipped iPhone to scan a target environment once, automatically generates navigation tasks, and uses the reconstructed scene geometry for reinforcement post-training, without needing manual teleoperation demonstrations.

    Why it matters: A single iPhone scan replaces manual demonstrations; 200 real-robot tests give a success-rate comparison from 25% to 85%, showing how post-training costs could fall.

  1. 3D视觉工坊 · 微信公众号78

    HKU open-sources GenSfM: jointly reconstructing 3D objects and camera poses from four uncalibrated images

    A University of Hong Kong team has open-sourced GenSfM, which uses a native 3D diffusion model to jointly denoise object shape and per-view camera poses within a single multimodal sequence, requiring only 2 to 4 uncalibrated images and no camera intrinsics or extrinsics. Evaluated on Toys4k and GSO, it improves novel-view PSNR by 3.2–4.5 dB over the multi-view baseline TRELLIS-M, reduces median Chamfer distance by about 64%–74%, and achieves pose Acc@5° above 96%.

    Why it matters: The work turns a native 3D diffusion model into the main inference mechanism for joint denoising of shape and camera poses, and releases code and models as a reference for sparse-view reconstruction.

  1. CMU Robotics Institute62

    CMU proposes Wiggle and Go: estimating physical properties of ropes by wiggling to plan manipulation

    A team at CMU's Robotics Institute has proposed the Wiggle and Go system, in which a robot first briefly wiggles a rope or cable while an overhead camera records how the waves propagate; a computer vision algorithm then tracks the motion and estimates the object's physical properties, which are used to plan subsequent actions without repeated trial and error. The model is trained entirely in simulation, and properties are then estimated from the motion of real ropes being wiggled to improve prediction accuracy on real hardware. The research has been accepted to the 2026 Conference on Robot Learning (CoRL) and will be presented next month in Austin; it is partly funded by the U.S. National Science Foundation.

    Why it matters: The method estimates a rope's physical properties from a single wiggle and then plans actions accordingly, offering a transferable approach to deformable object manipulation.

  1. arXiv cs.RO80

    Rendering-Free Event Frame Simulation Accelerates Reinforcement Learning for Autonomous Robot Navigation

    The authors propose an analytic event simulator that synthesizes event streams directly from scene geometry and ego-motion without image rendering, generating 64x64 event observations in just 17 microseconds on a single GPU, over 400 times faster than state-of-the-art rendering pipelines. Reinforcement learning training for an event-camera obstacle-avoidance policy based on this simulator converges in under 30 minutes, three orders of magnitude faster than training on rendered events, and transfers zero-shot to ray-traced event simulation in Isaac Sim.

    Why it matters: This work uses analytic event simulation to bypass image rendering, cutting event-camera reinforcement learning training time to under 30 minutes, and completes real-world deployment on a 56-gram drone.

  1. 机器之心 · 微信公众号76

    Ropedia Releases Six Research Results, Exploring How First-Person Human Data Can Be Turned into Robot Capabilities

    Ropedia released six studies at the first Ropedia Super Week, held October 19 to 23, centered on how first-person human video can be turned into training and execution information usable by robots.

    Why it matters: The six studies collectively address how first-person human data can be converted into training and execution information usable by robots, and present cross-embodiment and real-robot comparison results.

  1. arXiv cs.RO78

    RepresentNav: A Navigation Foundation Model Built on a Self-Constructed Representation Space

    The authors propose RepresentNav, a navigation foundation model that uses Representation Residuals, a three-layer transformer, to aggregate full-depth features from multiple vision foundation models and construct a representation space driven by the policy's own objectives.

    Why it matters: The paper proposes constructing a visual representation space using the policy's own objectives and predicting future scene representations within it, offering transferable ideas for the representation design of navigation policies.

  1. 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.

  1. Dexmate72

    Dexmate and CMU Release MeMoREval Benchmark: Robot Storing Camera Frames Beats Text Descriptions

    Dexmate and CMU introduced the MeMoREval benchmark, which uses a two-stage protocol of experiencing first and asking questions later to evaluate what embodied agents should store as memory. It includes 53 tasks and 4 simulated indoor environments, and runs on the Vega 1 Pro dual-arm mobile manipulator. Results show that storing raw camera frames scored 70% and had lower write cost, surpassing text descriptions at 56 to 60%; adding scene graphs achieved the highest overall success rate among all tested models. The protocol also completed two memory retrieval demonstrations on a real Vega 1 Pro using a SLAM map and head camera.

    Why it matters: The benchmark was proposed jointly by the platform developer and CMU; its frame-versus-scene-graph comparison can help with memory design choices, and the real-robot transfer offers a feasibility reference.

  1. CMU Robotics Institute68

    CMU research team develops human-inspired multisensory fingertips for DeltaHands robotic hand

    CMU researchers designed human-hand-inspired fingertips that can be mounted on the DeltaHands flexible robotic hand. They combine strain gauges to measure pinch pressure with a microphone that captures micro-vibrations through a plastic fingernail, enabling the hand to count paper cups, identify materials, and grasp fragile items such as tofu cubes and potato chips. Each fingertip costs less than 100 US dollars, compared with about 800 US dollars to build a similar setup from off-the-shelf products. The work was presented at the 2026 Intelligent Robots and Systems Conference in Pittsburgh.

    Why it matters: The original text provides details on the multimodal tactile design of the human-inspired fingertips and their cost of less than 100 US dollars, helping readers understand how force and vibration sensing support manipulation control.

  1. PKU EPIC Lab64

    PKU EPIC Lab proposes UniPart for zero-shot language-driven 3D part segmentation

    PKU EPIC Lab proposes UniPart, a feed-forward cross-modal 3D Transformer conditioned on CLIP text embeddings that uses free-text phrases to select functional parts on point clouds, achieving zero-shot language-driven 3D part segmentation.

    Why it matters: The paper presents a text-driven 3D part segmentation method and a self-built dataset, and validates transfer to real-world language-conditioned grasping.

  1. 加速进化 · 微信公众号72

    Tsinghua's Zhao Mingguo team publishes Science Robotics paper proposing a unified perception-motion reinforcement learning framework for vision-driven humanoid soccer skills

    On August 19, Professor Zhao Mingguo's team in Tsinghua University's Department of Automation published the paper "Learning Vision-Driven Reactive Soccer Skills for Humanoid Robots" in Science Robotics, selected for the August 2026 humanoid robotics special issue; the robot platform used was a humanoid robot independently developed by Booster.

    Why it matters: The paper breaks down three failure points of the traditional perception-planning-control pipeline and presents a reproducible sim-to-real transfer method.

  1. LeadeRobot77

    Mila and Polytechnique Montréal team open-source ~$2,000 robot guide dog Milo, built on Unitree Go2 for autonomous indoor and outdoor navigation

    Mila-Quebec AI Institute and a Polytechnique Montréal team have released Milo, an open-source robot guide dog that they say can cut the roughly $50,000 cost of a guide dog to about $2,000. The hardware base is a Unitree Go2 Air/Pro plus an NVIDIA Jetson Orin Nano; a magnetic-encoder telescoping handle is used to inversely solve the user's 3D position, a bird's-eye-view map is built first and then a navigation policy is run, and the policy is trained in about 10 minutes in GPU-accelerated simulation and deployed zero-shot on the real robot.

    Why it matters: The original article fully breaks down Milo's perception, policy training, and real-world testing details, so readers can reuse its engineering trade-offs in their own navigation projects.

  1. PKU EPIC Lab68

    WAM-TTT: Steering World-Action Models at Test Time by Watching Human Videos

    PKU EPIC Lab proposes WAM-TTT, a test-time training framework that steers world-action models from raw human videos without robot actions, human-side annotations, or task-specific fine-tuning. The method absorbs human videos into a lightweight adaptive memory inside a frozen WAM through self-supervised video prediction, and uses a meta-training stage with paired human-robot data and a key-value memory reconstruction objective to align human demonstrations with robot behaviors. Experiments show it consistently outperforms in-context human-video conditioning baselines across diverse manipulation tasks and generalization settings.

    Why it matters: The original work proposes a method for adapting a frozen world-action model at test time using only unlabeled human videos, without robot demonstrations or fine-tuning, offering methodological reference value for researchers who want to reuse it.

  1. 求之科技 · 微信公众号67

    GeoPredict makes VLA predict future trajectories and 3D geometry before generating actions

    The Chinese University of Hong Kong, Shenzhen and other institutions propose GeoPredict, which explicitly predicts end-effector and joint-level future trajectories before the VLA generates actions, and uses 3D Gaussian modeling for the geometry of the future workspace.

    Why it matters: GeoPredict incorporates future trajectory and 3D geometry prediction into VLA training, giving readers a spatial reasoning approach that does not increase inference overhead.

  1. New Scientist Robots76

    Sony AI table tennis robot Ace defeats professional players; research published in Nature

    Sony AI's autonomous table tennis robot Ace competed under the rules of Japan's professional table tennis league, defeating multiple elite and professional players; the research was published in Nature (DOI: 10.1038/s41586-026-10338-5).

    Why it matters: The article explains Ace's competitive record and three key technologies, and places it alongside the milestones of Deep Blue and AlphaGo, helping readers judge where physical sports competition currently stands.

  1. LimX Dynamics66

    GVF-TAPE Algorithm from LimX Dynamics and Partners Accepted to CoRL 2025, Enabling Robots to Learn Manipulation from Video

    The paper "Generative Visual Foresight Meets Task-Agnostic Pose Estimation in Robotic Table-top Manipulation," a collaboration between SUSTech CLEAR Lab, LimX Dynamics, and the University of Hong Kong, has been accepted to CoRL 2025.

    Why it matters: This research presents a concrete technical approach and experimental figures for learning manipulation from human video, helping readers understand the feasibility of training robot manipulation with video data.

You’re all caught up