9小时前更新
- 01Tuning StereoSGBM on PS5 Camera (ROS 2 Galactic) for Dense Depth MapsHi everyone, I’m working on setting up a stereo camera PS5 HD Camera in ROS 2 Galactic for stereo depth estimation using stereo_image_proc ( DisparityNode ), with the end goal of feeding the depth data into RTAB-Map for 3D reconstruction. I transitioned from StereoBM to StereoSGBM ( stereo_algorithm: 1 ) to handle the wide-angle camera setup better, but I’m having trouble finding the optimal combination of parameters which result in a dense point cloud with smooth surfaces. My depth output keepsVladimir_Privalov
- 02RobotCAD v12.10.0 is released!It’s been a long time since I posted any news. Many new features and fixes have been released. Here is a list of some of them that have appeared in recent versions. Added RobotCAD MCP server for agentic robot assembling. Updated Models Library. More models (219 now) and faster import . Added xacro and mjcf models import from Models Library. Added sensors field of view with reacting to sensor parameters. Other features and fixes: Fixed an error in collision creation for objects obtained via a linfenixionsoul
- 03Yeah Hand: open-source 15-DOF robotic hand with ROS 2 driverHi everyone, I’d like to share the Yeah Hand, an open-source, low-cost robotic hand with a ROS 2 driver. Video (50 s): https://www.youtube.com/watch?v=UgLujs26Dso Hardware 15 DOF, 5 tendon-driven actuators (Waveshare ST3215HS bus servos) Torque sensing on each finger, adaptive grasp 3D printed (TPU fingers and palm), ESP32 firmware, Bluetooth serial Mounting flanges for ISO 9409-1-50-4-M6 (UR, KUKA, Fanuc, Techman, Yaskawa), Agilex, ISO 9409-1-40-4-M6 and PCD-40 patterns License: CERN-OHL-S-2.0vittorio.lumare
- 04Has anyone found a reliable way to validate a hand eye calibration result?I have been trying to work out how a hand eye calibration should be validated and I have not found any complete answer yet There are some tools I looked at (MoveIt Calibration, easy_handeye, Kalibr) that just print reprojection error or transform, but I could not find a clear way to decide from that whether the result can be trusted or not. I read some of their GitHub issues and many people seem to end up in the same place “result looks off” and the only way to find out why is to ask someone morsanethdassanayake
- 05Boston Robot Hackers Oct 15 Meeting AnnouncementIn less than two weeks we will have our next monthly meeting of the Boston Robot Hackers . Mark it on your calendar now, and please register for the event—select October 15, 7:00 to 9:00. Our main speaker, Arjun Viswanathan will give a talk on Reinforcement Learning for Multimodal Locomotion. It promises to be a great and instructive topic of interest to many of us. If you’re in the area, I hope to see you! 1 post - 1 participant Read full topicpitosalas
- 06ROS News for the week of September 28th, 2026ROS News for the week of September 28th, 2026 ROSCon Global 2026 was last week in Toronto! There were a lot of big announcements, including Intrinsic releasing Intrinsic Open Core and wrapping up the AI for Industry challenge , PickNik and Qualcomm merging , Red Hat Enterprise Linux being elevated to a Tier 1 ROS operating system , and NVIDIA releasing Isaac ROS 5 . In other news, ROSCon Global 2027 will be held in Krakow, Poland . Videos from ROSCon 2026 should be out in a couple of weeks. On tKatherine_Scott
- 07Preparing for Lyrical Sync 2026-10-05Hello Lyrical maintainers! Starting now, I will be holding new Lyrical ros/rosdistro release PRs with a plan to sync ROS Lyrical packages to the main apt repo on 2026-10-05. Please comment here if there are any issues I should know about before performing the sync. There are currently 307 packages waiting to sync and 3 regressions . 1 post - 1 participant Read full topicsloretz
- 08ROS2 Parameter Value QueryingI need a much better way of grabbing the current value of every parameter of every node running on my system. Not just the dynamic ones, but the defaults and overrides from the launch system. From an experiment documentation standpoint, this is extremely important to understanding exactly how things are configured when producing data and later if data is changing figuring if one of these changed. Sure some nodes may be less important and their parameters not matter much, but there would remain mengnfrc
- 09MoveIt 2 Setup Assistant Tutorial: Custom 3-Joint Arm Troubleshooting Guide (ROS 2 Jazzy)Hello ROS Community, I want to share a comprehensive step-by-step video tutorial on configuring MoveIt 2 from scratch for a custom robotic manipulator on ROS 2 Jazzy and Ubuntu 24.04 . While most official tutorials use high-DOF industrial manipulators (like the Franka Emika Panda), building configurations for smaller or custom arms often introduces unique glitches that standard guides don’t cover ( 0:33 ). In this video, I take a 3-joint printed arm model ( arduinobot ) with a gripper ( 0:17 ),Prasad_Prabhu
- 10Control & state estimation contractor (NL, remote + on-site blocks)I’m Alex Andriën, an independent robotics engineer in the Netherlands (Andrien Robotics). I take on bounded, hard problems in control, state estimation and sensor fusion on real hardware: the part where it works in simulation and not on the robot. Typical problems: Localization that drifts or breaks without GNSS (drones, AMRs, underwater) Sensor fusion and calibration: IMU, camera, LiDAR, GNSS Controllers that are unstable, sluggish or fragile on the real platform Contact-rich manipulation whereAndrienRobotics
- 11Preparing for Jazzy Sync 2026-10-05We’re planning a Jazzy Jalisco sync next Monday Sun, Oct 4, 2026 4:00 PM UTC . There are currently 472 packages ready to sync and no regressions . If you find any other regression when testing, please report it upstream and leave a comment here so we can track it leading up to the sync. Starting today Thu, Oct 1, 2026 4:00 PM UTC we’ll hold all rosdistro PRs unless they fix reported regressions. 2 posts - 2 participants Read full topicmarcogg
- 12ROS PMC Minutes for September 29, 2026The ROS PMC meeting for this week was on Tuesday, September 29, 2026. The notes from the meeting are available at ROS PMC weekly meeting agenda . This was the first meeting back after ROSCon. ROS PMC Business REP 158 PASSES. The OpenUSD conventions for simulation asset interoperability are accepted. New committer candidates coming out of ROSCon. @robwoolley + @saikishor ROS Project Leader. October 1 is @mjcarroll ’s last day as project lead. @ahcorde has put himself forward as a candidate. Formamjcarroll
- 13ROS2 BuildHat Lego Spike/Prime Differential Drive ControllerDear all, BuildHat is a hardware interface (from the Raspberry Pi Foundation) between Raspberry Pi and Lego Spike/Prime. I have developed a differential drive controller package for this interface for ROS2. It subscribes to /cmd_vel receiving TwistStamped messages and controls the motors. Additionally it also publishes odometry. The package is configurable for different physical designs. I also include a demonstration package for Brian, the robot. It is a Python package, it does not use the ROS2jfrancis71
- 14Gazebo PMC Meeting Minutes 2026-09-28Hi Gazebo Community! This week’s meeting was held on Mon, Sep 28, 2026 6:00 PM UTC and the following is a summary: PMC Business Formal Decision: Accepted REP-158: OpenUSD Conventions for Simulation Asset Interoperability in Open Source Robotics . This was a joint vote with the ROS PMC, and the final results will be announced once officially recorded by both PMCs. A formal vote will be requested to sponsor Cherie Hu as a mentee committer. She has made significant contributions to gz-common . Newazeey
- 15Introducing NoDL: the Node Definition Language (ROSCon recap)TLDR: come work on NoDL in the rosgraph-wg . Join the mailing list for automatic calendar invites to meetings: https://groups.google.com/u/1/g/rosgraph-wg Hi everyone! @emersonknapp and I presented “The Legible Node” at ROSCon last week. We talked about two things: Thin nodes - your node is an interface adapter, it should not contain robot logic NoDL - the node definition language that allows you to statically declare your node interfaces If you didnt catch it, here are the slides (the_legible_nalistair-english
- 16September Meeting Reminder - TODAY at 4pm!Hi all, A reminder that our next working group meeting is coming up TODAY at 4pm . If you haven’t already, please take a look at Survey - Open Ocean Software and try to fill it out ahead of time. Survey results continue to inform WG direction, discussion, and opportunities for impact on the community. Here are the details: When: Last Tuesday of each month, 4–5pm EST This month: September 29, 2026 August agenda: OCEANS 2026 Follow-Up Discussion & Simulation Efforts This month we’ll be recapping Oivandor
- 17Complete the Open Robotics Annual Survey 2026 to enter the prize draw!Open Robotics has a survey asking for your feedback. Fill it in to enter a prize draw! Open Robotics works to support the development, distribution, and adoption of open-source software for use in robotics research, education, and product development. As an organisation and as a movement, we know a lot about the software, tools and standards that we build, but we do not know enough about the people who use them in their work, in their hobbies, and in their studies. What motivates people to use tgbiggs
- 18Computer Vision Engineer: Underwater Robotics - Remote friendlyWe’re looking for a robotics and computer vision engineer to help us build perception for the next generation of autonomous underwater robots. Our robots operate in conditions where off-the-shelf solutions often fall short, so this isn’t just about integrating existing packages. You’ll help design and build the perception stack, from SLAM and visual odometry to object detection and scene understanding, and take it from idea to code running on the robot. You will be joining our R&D team of 12 peojornb
- 19A Vulkan based SLAM(in progress) system that runs on Android/LinuxThis project currently stands as more of a proof of concept that it can run any arbitrary compute shader on a camera frame with zero copy than an actual SLAM/VIO,which I plan to implement eventually in the future.( Github ) 1 post - 1 participant Read full topicIceShuttle
- 20Open source SenseRobot Chess Clone - No ROS requiredHi everyone, Here is my custom-built Sense Chess Robot Clone! Inspired by the famous, high-end SenseRobot AI Chess Trainer, I wanted to see if I could replicate its physical piece-moving mechanics, AI vision tracking, and robotic arm precision using DIY components. SenseRobot Chess Clone Robot’s information: Components & Software Used Microcontroller: Arduino Mega 2560 + RAMP 1.5 CPU: Intel NUC 7 Celeron J4025 Motors: NEMA Steppers + GM12-15BY Steppers Camera Sensor: Full HD Webcam Chess Engine:NguyenHoang_Hai
- 21Linorobot2 Cockpit: In-Browser Web Supervisor, Turnkey micro-ROS & 1-Click Nav2 Autonomy (Call for Testers)Hi ROS community, We are excited to share Linorobot2 Cockpit GitHub - hippo5329/linorobot2-cockpit: 1-Click mobile robot autonomy from browser to bare microcontroller: unified micro-ROS firmware, realistic physics simulation, SLAM & Nav2 supervisor. · GitHub (release v2026.09) and invite developers, researchers, and roboticists to test out the platform and share feedback! Linorobot2 Cockpit is a containerized, browser-based supervisor for ROS 2 mobile robots. It provides a unified web control stThomas_Chou
- 22Layer 3 Negation Hardening: Resolving Ranking Inversions in QERRA-THRIVE (v2.0.2)Hi everyone, Following up on my previous post on Layer 1 (Webots Demo 6), I wanted to share the second half of the v2.0.2 release for QERRA-v2 Classical: universal negation hardening and ranking inversion fixes across all 12 vectors in Layer 3 (QERRA-THRIVE) . Layer 3 serves as the values-based preference ranker in QERRA. When an autonomous planner generates candidate action plans, Layer 3 evaluates and ranks them across 12 behavioral vectors ( Suite A: Human-Centered and Suite B: Ecological ) umarunigno-ship-it
- 23Mission Canvas — Turn Robot Skills into Real-World TasksAI WORKER #21: Mission Canvas — Turn Robot Skills into Real-World Tasks A robot performing an isolated skill is only part of a real-world application. It also needs to move to the right location, execute the right task, and continue to the next work area as part of a repeatable workflow. This video introduces Mission Canvas. It lets you define waypoints on a map, specify their order, and connect a Task to each location so navigation and robot actions can be executed as a single Mission. The relaPyo
- 24Community Meeting #64 - September 28th, 2026 @ 3pm UTCI have returned home and am still recovering from an epic ROSCon Global. Looking forward to filling everyone in on how it went. We also have a chock full list of new topics to explore: Layer Audit ROS World builds / skip groups Superflore Transitive Dependencies SDK Documentation OEROS Container Images Support for Edge AI bitbake-setup OE Config Fragments See more details here: Community Meeting #64 - September 28th, 2026 @ 3pm UTC · ros/meta-ros · Discussion #1841 · GitHub I have drafted some srobwoolley
- 25Shared_buffer_backend: shared-memory rosidl::Buffer for ROS 2 processesshared_buffer_backend: shared-memory rosidl::Buffer for ROS 2 processes I would like to share shared_buffer_backend , an experimental CPU shared-memory backend for rosidl::Buffer . This follows my earlier discussion about a CPU shared-memory backend , and was previously called memfd . The goal is to make large, variable-length payloads such as images available to nodes in separate processes, including Python nodes, without transporting the payload bytes themselves through the normal message pathDaisuke_Kato
- 26Question on local vs. remote inference placement for perception tasksHey all! ECE undergrad here, exploring an inference-routing idea for robots (deciding at runtime whether a perception or higher-level AI task runs onboard, on a nearby edge server, or in the cloud, based on deadlines, network conditions, and local compute load) and trying to validate the problem before building anything. For those running real robots: is your local/remote split for perception or AI tasks fixed, or does it ever change dynamically? Has latency or local compute contention ever actujohan784
- 27Webots Demo 6: Compound Physical Safety Reflex on TIAGo (QERRA-v2 Classical)Hi everyone, Following up on my previous posts on deterministic safety layers, I wanted to share the latest simulation demo (Demo 6) from my work on QERRA-v2 Classical, focusing on Layer 1 (the physical safety reflex, QERRA-HSR v0.1 ). The purpose of this layer is to act as a lightweight, deterministic safety companion that handles two specific jobs: Clamping wheel motors immediately with zero ML latency when an acute physical emergency occurs. Enforcing a safe recovery policy once conditions clmarunigno-ship-it
- 28Ros2_unbag is now available via the ROS 2 buildfarm 📦Hi everyone, A small-but-important update for ros2_unbag Starting with v1.3.0 , ros2_unbag is now released through the official ROS 2 buildfarm. That means installation is now as simple as: sudo apt install ros-<distro>-unbag and then: ros2 unbag No separate pip install, no cloning, no building from source — just a regular ROS package. For anyone who hasn’t come across ros2_unbag yet: Your robot packs the bags; ros2_unbag brings them to your room, unpacks them, and sorts out the mess. No lost lulostendo
- 29Aerial Robotics Meeting - October 1st 2026Hi ROS & Aerial Robotics Community! Greetings from ROSCon Global 2026 ! As part of our working group updates this week, we are thrilled to formally announce our next Aerial Robotics Working Group meeting. Date: Thu, Oct 1, 2026 5:00 PM UTC → Thu, Oct 1, 2026 6:00 PM UTC Meeting Link: Google Meet Link Anel Olivares Cruz (Area of Computing and Electronics, Autonomous University of the State of Hidalgo) will present us " Self-tuning neuromorphic controller for real-time UAS trajectory tracking baseTOTON95
- 30Assistant Research Engineer (AI/ML) - MATRIX Lab - University of MarylandNot me, but a local lab for UMD is hiring a AI/ML researcher who will work very closely with ROS 2 and simulation stacks like Gazebo/Isaac Lab in flurry of robotic use cases (I know for a fact, mainly UAVs and UUVs). The corresponding LinkedIn post and Workday applications provide more info (responsibility, objectives, location, and pay). They do really cool, fun work though. Linkedin Post: The University of Maryland A. James Clark School of Engineering’s MATRIX Lab is expanding its team! We areCursedRock17
共 30 条热搜查看完整榜单