#机器人
200
2026-09-23
Show HN: InstinctFlash – High-Performance Serving Runtime for Robotics Models
A
Hey HN, Guanming here, cofounder of General Instinct. We just released InstinctFlash, a high-performance serving framework for robotics models. It’s licensed under AGPL-3.0. On Jetson Thor, we see speedups about 1.2x to 7.9x from runtime optimizations alone and up to 33.78x for LingBot-VA when we combine those runtime optimizations with a distilled few-step diffusion scheduler, going from the original 25 visual / 50 action steps to 2 / 4 steps. Across 50 Robotwin2.0 tasks, we evaluated 1,153 episodes per configuration, LingBot-VA with InstinctFlash at 2 visual / 4 action steps achieved a 90.5% success rate, compared with 92.1% for the baseline at 25 visual / 50 action steps. Here’s an optimized 5B world action model, running in real time on a Jetson Thor: https://youtu.be/nku65iyL5Fw InstinctFlash currently supports 8 VLA / world-action model families, including pi0.5 and NVIDIA Cosmos Policy, across RTX 4090 / 5090 and Jetson Thor. Just give it your fine-tuned checkpoint and InstinctFlash handles the rest, exposing the accelerated model through a Python runtime or an OpenPI-compatible WebSocket server. We started working on this because we kept running into the same problem while deploying robot policies, the models were getting much better, but inference was often way too slow for the control loop we actually wanted. For pi0.5, mixed-precision GEMMs and CUDA graphs speed up computation and reduce launch overhead. For Cosmos, caching avoids redundant computation across diffusion steps. World-action models’ diffusion denoising step depends on the previous one which motivated our work on few-step distillation. Right now, InstinctFlash contains 6 aspects of optimization. - Graph: CUDA graph capture, memory planning and separating prefill from repeated execution. - Cache: Reusing KV and conditioning state across diffusion steps and prediction calls. - Attention: Specialized attention paths for different model architectures. - Kernels: Fused operations and kernels tailored to specific backends and tensor layouts. - Precision: FP8 and mixed-precision execution. - Model: Few-step distillation for diffusion and action generation. Teams at Samsung, Siemens, and other robotics startups have used InstinctFlash for model acceleration on VLAs, WAMs, and diffusion-based world models. Now we are opening up access to you. Feel free to try it here: https://github.com/General-Instinct/InstinctFlash More implementation details and benchmarks: https://general-instinct.com/blog/instinctflash-edge-inferen... Would love to hear your feedback!
2026-10-28
jlcjak/neurband
S
Open, minimal sEMG wristband like the Meta Neural Band: 8-ch ADS1298 + nRF52832 BLE, dry gold electrodes on a flex, 3D-printed band. KiCad, FreeCAD, Zephyr, Python, simulations.
2026-11-04
yzytz17/1.5-joint-module
A
Ultra-low-cost robotic joint: a $1.5 FOC board inside a 1503 gimbal motor, plus a 3D-printed high-ratio precision gearbox. Cheap power, exact motion.
2026-09-16
Fenon-Robotics/egodup
A
Local-first detection and temporal localization of reused footage in egocentric video.
2026-11-04
fuyichen0725/blinkmimic
A
Whole-body motion tracking for the Unitree G1 in about 3 minutes on one GPU.
2026-09-18
jianglongye/dexterous-astra
A
Dexterous pen spinning and Rubik's cube: sim environments, zero-shot scripts, trained checkpoints
2026-09-11
kevinzakka/mjbatch
B
A Python library for running thousands of MuJoCo simulations in parallel on CPU
2026-08-28
OpenBMB/SimpleNav
A
SimpleNav: A simple, unified, reproducible, and extensible framework for navigation VLA research.
2026-11-09
nico-bohlinger/xmimic
A
Whole-body motion tracking for the Unitree G1 in under a minute. BlinkMimic's world-model trainer rebuilt in JAX, 3.5x faster on four H100s.
2026-10-29
Z-billi/roboArm
A
Open-source robotic arm: SolidWorks CAD models, Arduino UNO firmware and Python/PySide6 desktop control. MIT licensed.
2026-10-24
suniique/assembly-nist
A
[Assembly NIST] Assembly policy learning for a Franka arm in MuJoCo. Independent implementation of AlphaNIST with PPO, training code, and pretrained policies.
2026-09-30
Show HN: JBR-001 – An open-source 3D printable desktop robot
B
We built a desktop companion robot that is powered by Arduino UNO Q. Project is open source: source code, 3D printable files and assembly instructions are available at Arduino Project Hub. Robot is equipped with camera, distance sensor, buzzer, moves head and arms with 3 servo motors and has an animated display. It can recognise objects and respond to it. We build it with idea this should be fun project people can 3D print and build at home themself.
2026-10-30
Huy-Quang-Dao/instantTrack
A
Whole-body motion tracking for the Unitree G1 in 15 minutes on one GPU (SuperMimic-style world model + InstantMimic-style GPU loop, mjlab)
2026-09-26
Mondo-Robotics/open-beni
A
OpenBeni browser robot racing with MuJoCo WebAssembly, ONNX policies and training source
2026-09-05
YibinWu/DogLegs
A
[IROS 2025] DogLegs: Robust Proprioceptive State Estimation for Legged Robots Using Multiple Leg-Mounted IMUs
2026-08-28
affirmitv/ghosthands
A
Give an agent real hands and eyes: undetectable, DOM-independent GUI automation. A $4 USB-HID microcontroller for hands, a vision grounding model for eyes, any LLM for a brain.
2026-10-16
mbzuai-nlp/ChemLab-Assets
B
198 simulation-ready chemistry lab instruments: part-level geometry, joints, executable behaviour models and machine-readable contracts
2026-10-10
swirl-uk/BiGym2
B
BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation (arXiv:2610.07594)
2026-09-30
12-Twelve-12/robolings
B
Small exercises for robot learning, rustlings style: kinematics, dexterous hands, control, diffusion policy, flow matching. NumPy only.
2026-09-14
yuhyun00/SoftCorr
B
Official Implementation of SoftCorr: Differentiable Local Correlation for Single-Frame Targetless LiDAR-Camera Calibration
2026-11-04
Open-RUA/uni-robot-agent
B
Democratizing Robot-Use Agents: A Unified Harness with Open Models
2026-10-17
Stanford-TML/FoveaVLA
B
Official code for FoveaVLA: Foveation Actions Replace the Wrist Camera in VLAs
2026-09-24
roboto-ai/roboto-physical-ai-actions
B
Roboto actions for physical AI: curate and audit robotics data, convert it to LeRobot (v2.1, v3.0) datasets, merge, up- and down-convert them
2026-09-19
dimentary/llm-robotics-playground
C
A library of experiments using frontier LLMs/VLMs for robotics tasks, currently focusing on GPT-6 Astra.
2026-09-18
Daniel-rmc/ManiLoop
B
An open framework for closed-loop evaluation of VLA, VLM, and other robot policies across benchmarks, designed for fair and reproducible comparisons. Current integrations: MuJoCo tasks, LIBERO, GPT, and LeRobot.
2026-09-16
YueBit/robodiag-harness
B
AI diagnostic agent for ROS 2 robots — evidence-based, tool-calling, safety-gated.
2026-10-23
Motphys/Uni-SuperMimic
C
SuperMimic-UniLab: An Independent reproduction of SuperMimic on UniLab for whole-body humanoid motion tracking.
2026-09-30
gentlefress/OMEGA-0
C
The offical code of ω-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation
2026-09-17
fuxingyin/scan2mesh
B
Scan2Mesh is a high-performance mesh-based LiDAR localization and tracking system that estimates LiDAR poses by aligning incoming scans with a pre-built 3D mesh.
2026-08-31
mrzuang/GRIT_teleop_deploy
B
This repository provides Unitree G1 deployment code for GRIT v0.0.1, a whole-body motion-tracking control algorithm for humanoid robots.
2026-10-15
Virlus/VaM
B
Official implementation of the paper "Value as Memory: Online Value-Guided Post-training for General Robot Policies"
2026-10-14
rzc156/dreamforge
C
Turn world-model imagination into corrective training data for robot policies — a single-GPU, falsifiable pipeline (SmolVLA · LIBERO · CEM · paired simulator replays).
2026-09-18
7757/fanduck
B
超能花钱鸭 Fanduck · Microduck 已复刻成功！分享实机演示、物料清单、3D 打印、板件、制作工具与 3D 镜像工作台。Build resources from our completed Microduck replica.
2026-08-28
hku-sail/StreamPI
B
StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models
2026-10-28
kaibohex/muscle-supermimic
B
SuperMimic whole-body motion tracking for muscle-driven humanoids on mjlab.
2026-09-25
declare-lab/MemBodied
B
Recurrent associative memory for vision-language-action models. Official implementation of MemBodied.
2026-09-12
thedhruvhegde/nadir-core
B
Open-source ADAS sensor drift scoring (Pulse/Echo). Shadow mode. Apache-2.0.
2026-08-28
robbyant-research/Zero-WAM
C
In‑Context World‑Action Modeling from Human Videos for Open‑Ended Task Generalization
2026-10-15
AutoLab-SAI-SJTU/WAVE-0
B
Official repository of "WAVE-0: Bridging VLA Policies and WAMs with Lightweight Latent Future Prediction"
2026-09-07
frankWang67/EmbodiSteer
B
[CoRL 2026] EmbodiSteer: Steering Embodiment-Agnostic Visuomotor Policies with Joint-Space Guidance for Zero-Shot Cross-Embodiment Deployment
2026-09-06
microai-lab/microduck-studio
B
Local web studio for developing, debugging, visualizing, and safely orchestrating Microduck robot and reinforcement learning workflows.
2026-09-04
PINE-Lab-NTU/FACET
B
Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation (arXiv 2609.01596)
2026-08-27
Matheshwaranpitchai/open-source-leader-arm
B
open-source, low-cost, 3D printed leader arm for teleoperating an SO-ARM
2026-10-09
roboterax/video-prediction-policy-2
B
Official implementation of Video Prediction Policy 2: Predict Better, Act Better
2026-10-26
Baojch/SuperMimic_Dyn
B
基于 SuperMimic 复现与适配，在 MuJoCo 闭环仿真中实现前空翻、后空翻、侧空翻、侧手翻等高动态动作，并支持爬行、跌倒起身与全身动作跟踪。
2026-10-07
zhuoligetu123/microduck-hd1910m
B
Radxa ZERO 3W + 飞特 HD1910M ×15 + BNO08x。包含行走、拾取、起身、翻滚四模型适配、Rust 后端/底层、RL 训练与 MuJoCo 仿真源码；客户端APK。 MicroDuck HD1910M native runtime, RL integration, deployment and APK release
2026-09-19
HengyiWang/amb3r-slam
B
[arXiv'26] AMB3R-SLAM: Kilometer-scale SLAM with Hierarchical Backend
2026-08-24
ChiyunNoh/TRaIL-Odom
B
[RA-L 2026] TRaIL-Odom: Tightly Coupled Continuous Time Radar-IMU-LiDAR Odometry with Adaptive Doppler Weighting
2026-10-23
Show HN: Impossible Machines: declaratively program the physical world
C
Hey all — Sharing a thought experiment I put together. The premise: what might declarative programming feel like for the physical world? We’re already familiar with this paradigm in software land (eg SQL etc where we declare what we want and the execution engine figures out how). I didn’t have access to an actuator so I mocked up the concept in software. The way it works is you demonstrate the effect and the system figures out how to achieve it. So say you want to ring a bell and you have a crank. The system will find a way to connect the two. If you add obstacles it figures out how to work around them (runs a constraint solver runs behind the scenes). I think what’s interesting about this is being able to think about the problem at a higher level of abstraction, with the system figuring out a way to achieve the intended effect. Anyways, curious to read reactions, feedback, and interesting ideas on how to extend this!
2026-09-13
jiejie567/rethink-lio-gravity
C
Controlled gravity and accelerometer-bias ablations in FAST-LIO2 and LIO-SAM: code, evidence and video.
2026-09-13
shengshu-ai/Motus2
C
Motus2: A Self-Evolving General World Model for Dexterous Manipulation
2026-08-30
rokbenko/quackd
C
🦆🧠 Give your Microduck a brain. Tell a small robot with two legs what you want in plain language. An LLM (Claude, OpenAI, Gemini, Grok) uses the skills it already has to do it. Includes a simulator, .duck task files and MCP. Apache 2.0 license.
2026-10-27
CumulusAlpha/Dex-Supermimic
C
This is a reproduction of SuperMimic for dexterous hand manipulation task.
2026-10-26
BioNanomics/openflexure-light-sheet
C
Student-led BioNanomics light-sheet microscopy project based on SPIM-DoMB and OpenFlexure sample positioning.
2026-10-22
Cyberyyc/HoloSplat-3DGS-Robot-Digital-Twin
C
3D Gaussian Splatting scene registration and ROS-driven mobile-manipulator digital twin modules for HoloLens spatial interaction.
2026-10-21
No-518/Tactile-ETA
C
Tactile-ETA: tactile in-context learning for fine robotic manipulation
2026-09-29
zhuxun132/InJepa
C
InJepa: Intention First Latent State Planning with Coupled JEPAs for Visual Navigation. Code, Clean150 tasks and E12 checkpoint.
2026-09-18
patchx2027/Patchx-OpenDeskRobot
C
Patchx-OpenDeskRobot is an open-source desktop companion robot, built by the PatchX team for our own desks. It listens, talks, and reacts with expressions and motion.
2026-10-22
Cyberyyc/HoloMotion-Spatial-Robot-Teleoperation
C
Head-aligned spatial robot teleoperation with hand-pose tracking, quaternion motion commands, clutching, and ROS integration.
2026-09-27
tsadja/morphometric
C
Morphometric Imitation: From Morphology and Contact Aware Hand Retargeting to Sim-to-Real Visuomotor Policy
2026-10-25
CH-LaTiao/lumina-guide
C
LUMINA Guide / 灵犀: Jetson + Orbbec RGB-D wearable navigation assistant prototype
2026-10-08
hgupt3/eigendexplore
C
Official code release for EigenDEXplore: Structured Exploration for Dexterous Manipulation with Human Priors. https://eigendexplore.github.io/
2026-09-27
Sirui-Xu/ULTRA
C
[IROS 2026] ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation
2026-09-13
ashleyotooligan/ant-1
C
An embodied neural experiment connecting a simulated ant to a synthetic neural controller
2026-08-31
joeynyc/awesome-microduck
C
A curated list of software, simulators, policies, agent tools and coverage for the Pollen Robotics / Hugging Face Microduck robot
2026-10-16
Interactive-Active-AI/OneWM
C
:one: OneWM: Can World and Action Modeling Benefit Each Other under Unified Causal Training?
2026-10-16
HY-LiYihan/agentic_rsr
C
Agentic RSR: Real-to-Sim-to-Real through Scene Reconstruction and Execution-Grounded Robot Policies
2026-10-07
mose3-tracker/MoSE3
C
[NeurIPS 2026 Spotlight] MoSE3: Learning World-Space SE(3) at Every Pixel
2026-09-17
SpikeCalls/FlyDrones
C
A fruit fly connectome as a drone pilot. Camera -> fly eyes -> spiking brain -> descending neurons -> drone. Live 3D demo in your browser.
2026-08-27
linhanwang/GlanceWAM
C
Repo of "GlanceWAM: Sparse Test-Time Imagination for World-Action Models"
2026-10-27
alibaba-damo-academy/RynnUnify
C
Agentic Embodied Intelligence via Reciprocal VLM Reasoning and World Modeling
2026-10-23
zhangy0822/CofactVLA
C
CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention
2026-10-08
Daniel-xsy/safedrive-vla
C
[CoRL 2026] SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving
2026-10-05
PhysicalAIBenchmarks/Text2WetLab
C
Anthropic Science Lead: the gap in the next 2 years, will be the orchestration layer of taking experiments described in natural language and orchestrating them in the real world. The two orchestration layers we will test L1 and L2 is liquid-handling and fine-grained instructions.
2026-09-21
fabriciowth/cozmo-esp32
C
Robô de bancada com ESP32: rosto animado no OLED, conversa por voz em pt-BR, jogos e controle do Mac
2026-09-14
ajisrawi/dronemagnav
C
Magnetic-anomaly navigation (MagNav) board + firmware for drones: ESP32-S3, BMI088, LIS3MDL, BMP280, u-blox GNSS, WDMAM map matching, particle filter, MAVLink, phone route planner. Proprietary - all rights reserved.
2026-09-13
hx23840/S3-PX4-FC
C
ESP32-S3 flight-controller hardware designed by Peter using Codex + GPT-6 Astra. EasyEDA project and manufacturing files in Releases.
2026-10-24
JackMin7/supermimic_whole_body_tracking
C
在同一静态站立任务上，对比 MBRL（SuperMimic） 与 PPO（原版 BeyondMimic），两组各累计训练约 1 小时。
2026-10-02
Random8756/Bench2Drive-RLinfra
C
Scalable reinforcement learning infrastructure for autonomous driving, supporting privileged planning and end-to-end policy RL post-training in CARLA.
2026-09-21
FBddcz/embodied-jev
D
EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs
2026-09-15
Frankweb33/flybrain-robot-bridge
D
Experimental Drosophila-inspired camera-to-robot bridge. Working mock neural backend, optical flow, IMU feedback and UDP motor control. MaleCNS integration planned.
2026-09-11
MarkUnthank/flyhard
D
A connectome-based fruit fly physically learning to operate a steering wheel in CARLA
2026-09-04
Vottivott/microduck-playground
C
Reproducible MicroDuck RL experiments, policies, simulation assets, and hardware add-ons
2026-10-23
xuyicheng-zju/TARSphere
C
A robot-oriented full-stack framework for long-horizon embodied agents in evolving physical and social environments.
2026-10-02
amazon-far/PRISM
C
[CoRL 2026] Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation
2026-09-27
WB-WaM/WB-WAM-Official
C
WB-WAM: Heterogeneous Body–Hand Pre-training for Humanoid Loco-Manipulation.
2026-10-10
Dishank1501/robot-fleet-analytics
C
Interactive robot fleet performance analytics dashboard using Python, MySQL, Pandas, NumPy, Plotly, and Streamlit.
2026-09-13
EsiSeraj/robot-learning-fieldbook
C
A robot learning field guide with notes, mechanisms, diagrams, runnable code, flashcards, and drills...
2026-09-03
cmjang/GMTrack
C
Extreme-RGMT: continual learning of highly dynamic skills for robust generalist humanoid control
2026-09-03
oplisty/RoboPrep
C
Embodied AI interview preparation platform: interviews, knowledge, ML coding judge, company intelligence
2026-10-23
CuboiLeo/SuperMimic-Reproduced
D
Reproduction of SuperMimic (arXiv:2610.28480): learned differentiable world model + BPTT policy for G1 humanoid motion tracking, on mjlab/MuJoCo Warp
2026-09-24
ThinkFlowLab/system1-agents
C
System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics
2026-09-24
shapsider/OmniJev
C
OmniJev — multimodal finite-choice decision interface and MuJoCo embodied workbench: trajectory replays, decision probes, benchmark panels, 60s walkthrough.
2026-09-10
YanjieZe/SR-Paper-List
C
Robot learning papers in Science Robotics (2024–2026), with verified cover papers and a searchable directory
2026-09-19
OrangeRangeAngeNge/Demo2Skill
C
Demo2Skill: Learning Human-Like Robot Manipulation Using GPT as a Coding Agent
2026-10-22
Island-Team/Aether-EOS-R
C
The robot runtime for IslandOS Aether, connecting hardware, perception, and skills through shared interfaces for robot state and actions.
2026-10-25
justxor/robotics-roadmap-2026
D
Открытый курс: собери первого робота и войди в робототехнику с нуля за 6 месяцев. Электроника → Arduino/ESP32 → CAD и 3D-печать → рука SO-101 → ROS 2 (SLAM, Nav2) → PID/LQR, CV → LeRobot. 100+ ресурсов, схемы, готовый код, железо на 3 бюджета, план по неделям и 30 идей проектов
2026-09-08
quymom941478/KyThuatUAV_ESP32_FC
D
nghiên cứu và phát triển bộ điều khiển bay drone dựa trên esp32
2026-08-28
zhengzihaoPKU/Awesome-Embodied-Trustworthy-Execution
D
Survey and Taxonomy of Embodied-Trustworthy-Execution
2026-09-27
SUZ-tsinghua/awesome-humanoid-ball-sports
D
A curated list of humanoid robots playing ball sports: table tennis, tennis, badminton, soccer, basketball, with a map of who works on what
2026-09-24
GehaoZhang6/Grounded-Action-Model
D
Grounded Action Model: 3D Grounding as a Foundation for Robotics (code coming soon)
2026-10-03
benmagnifico/DriveJev
D
An open-source, efficient System I decision model for autonomous driving.
2026-09-19
griffinlabs-ai/alpha-s
D
Foundational vision-language action (VLA) model by Griffin Labs.
2026-09-11
showlab/Awesome-Multimodal-Embodied-Agent
D
Survey on Multimodal Embodied Agents: From Computer-Use to Robot-Use
2026-09-24
Haaareally/AdaHVLA-Adaptive_Harness_VLA
D
AdaHVLA connects task-level reasoning and memory with vision-language-action (VLA) execution through an adaptive harness. Preprint version of our paper is coming soon. The real-world deployement part is coming soon as well!
2026-08-31
HKUST-Aerial-Robotics/FC-Family
D
A Series of Research on Advancing Aerial Robots Beyond Mobility
2026-08-24
alphaparkinc/genpark-lidar-d-shape-autonomous-floor-mapping-robot-skill
D
Laser LiDAR SLAM floor mapping and D-shape robotic vacuum cleaner (Neato style)
2026-09-19
Ani579/Obstacle_avoid_bot
D
This is the project for arduino obstacle avoiding robot made via ARDUINO UNO, L298N MOTOR DRIVER, SONAR HC-SR04, SERVO MOTOR. Use the drive link to see the 30sec simulation video which I made for you guys.
2026-09-22
YuanKJing/Jev-as-Policy
D
The highly anticipated open-source repository for JEV as Policy enables one-click setup of the simulation environment. Evaluations of Astra + JEV on benchmarks such as RoboTwin will also be released soon.
2026-09-25
MIT-CDFG/Survey-AI-for-3D-modeling-Robotics
D
On the Opportunities and Risks of Frontier Models for 3D Modeling, Computational Design and Robotics (MIT CSAIL CDFG)
2026-09-20
khordoo/jev-reflex-autonomy-lab
D
Multi-drone autonomy lab demonstrating TypeSafe Jev reflex decisions with optional System 2 strategy guidance.
2026-09-18
RomanSlack/jev-drone
D
Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz
2026-09-21
Dimweaker/jev-libero
D
Fine-grained robot control with Jev, physics previews, and configurable LIBERO tasks.
2026-11-09
google-deepmind/mujoco
未评级
Multi-Joint dynamics with Contact. A general purpose physics simulator.
2026-11-06
CGmoke/robot-forge
未评级
A robotics monorepo: ROS 2 real-robot humanoid application plus reusable Python libraries for geometry, occupancy grids, kinematics and tracking.
2026-11-06
sailab-ai/NablaMimic
未评级
Ultra-Efficient Humanoid Control with Differentiable Simulation.
2026-11-05
FlashCat-Jordan/Flashduck
未评级
闪猫造物Flashduck — an open-source ESP32-S3 desktop duck robot with six servos, a single animated eye, wide-stance walking and two interaction systems (voice assistant / DuckClaw local agent).
2026-11-04
ASIG-X/JEPLO
未评级
First JEPA-based learning framework for mapping-free LiDAR-based perceptive locomotion
2026-11-04
AetherLabsAI/RobotAgentBench
未评级
RobotAgentBench: A benchmark for evaluating open-world robot autonomy in realistic household environments.
2026-11-04
vinceyuchen/Perceptinet
未评级
CARLA-based cooperative perception system integrating YOLO26n, V2I communication, sensor fusion, TTC risk assessment, and automated braking.
2026-11-03
metacognitionai/NavGPT-3
未评级
Official implementation of NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime
2026-11-02
HetaoLu-Creater/uwb-localisation
未评级
Real time UWB localisation for small spinning robots on a tabletop play field, from ranging hardware to live position display. Includes calibration for each anchor, Kalman tracking, a browser dashboard and offline replay, together with the experimental data.
2026-11-02
tuotuoLyu/FPO
未评级
Official code for "Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models" (ICRA 2026): Flow Policy Optimization for pi0
2026-10-31
Gamma-Robot/bfm_ttc
未评级
Code for Test-Time Compute for Humanoid Behavior Foundation Models