Understanding why autonomous robots do what they do can be a very difficult task to understand. At its core, Foxglove is a visual analysis and debugging tool for multimodal data; the data a robot produces as it perceives the world. Examples: lidar scans, depth images, RGB camera feeds, sonar, 3D maps (indoor and outdoor), bounding boxes that represent objects (static or dynamic) the robot has encountered, segmentation images, radar, time-series, and much more… Understanding robots requires so much more than the text and time-series we’ve become so accustomed to over the years building cloud infrastructure and applications. Text and time-series simply won’t help you understand why the robot thinks something to be when in fact it might not be. You also need to visualize live and recorded streams of data over time to triage incidents, improve and test your models, and repeat. There are so many factors to consider when understanding a robot's action: like environmental, temporal, etc… that could lead the robot to detect an object in the wrong way, or take the wrong path. It could even possibly be a bug in the software from the latest update. The power of visualizing all the data and being able to traverse it over time enables you to debug quickly and better understand how your robots sense, think, and act. But it also sparks ideas to innovate and improve, along with the empowerment to make the idea come true. The nuScenes dataset is a public large-scale dataset for autonomous driving developed by the team at Motional. Link to the dataset and to learn more about Nuscenes in the comments.👇 #DataViz #Analytics #Robotics
Foxglove
Software Development
San Francisco, CA 8,739 followers
Visualize and manage multimodal data in one purpose-built robotics development platform to build better robots, faster.
About us
Foxglove is pioneering a new era for robotic development and embodied AI. Our powerful interactive visualization and data management capabilities empowers robotic developers to understand how their robots sense, think, and act in dynamic and unpredictable environments. All with the performance and scalability needed to create autonomy and build better robots, faster.
- Website
-
https://foxglove.dev
External link for Foxglove
- Industry
- Software Development
- Company size
- 11-50 employees
- Headquarters
- San Francisco, CA
- Type
- Privately Held
- Specialties
- Multimodal Data Visualization, Multimodal Data Management, Robotics Development, and Autonomous Robotics Development
Products
Foxglove | Robotics Data Visualization and Management
Data Visualization Software
Understand how your robots sense, think, and act through Foxglove's multimodal data visualization and management platform. * Connect directly to your robot or inspect pre-recorded data. * Use interactive visualizations in customizable layouts to quickly understand what your robot is doing. * Overlay 2D and 3D images with lidar, point cloud, and other sensor data incl. annotations and bounding boxes to see what your robot sees. * Display and control robot models in interactive 3D scenes to understand how your robots move through the world. * Analyze everything as you travel through your robots mission and journey with Timeline and events. * Build bespoke panels, convert custom messages, and alias topic names to support your team’s unique development workflows. * Use Foxglove offline, store your data at the edge, then in your cloud or ours —no matter what your connectivity or data constraints are.
Locations
-
Primary
San Francisco, CA, US
Employees at Foxglove
Updates
-
Nick Obradovic will tell us live at #Actuate2024 how he and Sanctuary AI are navigating uncharted territories to train general purpose humanoids to solve real world problems. Get your tickets today 👉 https://buff.ly/3Rnfteb 🎟️
-
Striking a balance among maintaining optimal sensor performance, minimizing operational downtime, and preserving onboard resources has become trickier than ever for perception engineers working on autonomous vehicles. 🚘 Come to #Actuate2024 and hear Jeremy Steward, Senior Software Engineer, Tangram Vision, talk about the different technical aspects of both "offline" and "online" (or fully autonomous) calibration configurations, and evaluate how each of these provide different technical, performance and operational advantages (or disadvantages) on both the production line and in the field. Get your tickets right now 👉 https://buff.ly/3Rnfteb 🎟️
-
ADAS engineering seamlessly integrates diagnostics, planning, control, and perception. Core to this field is the synthesis of electrical and mechanical diagnostics with advanced planning and motion control algorithms, allowing vehicles to navigate dynamic environments effectively. 🚘 Key technologies such as 3D deep learning and computer vision are essential for optimizing trajectories and predicting road user behavior. These technologies transform strategic driving plans into adaptable, executable actions. Critical to robust perception systems are spatio-temporal machine learning models for tasks like object detection, sensor fusion, and semantic segmentation. Engineers leverage advanced video processing, predictive analytics, and comprehensive sensor data integration to build systems that accurately interpret and respond to environmental cues. Managing and visualizing all of the data needed to properly understand your systems is streamlined with Foxglove. Leveraging customizable layouts brings all the data together for the real-time analysis needed to develop performant ADAS systems. The nuScenes dataset is a public large-scale dataset for autonomous driving developed by the team at Motional. Link to the dataset and to learn more about Nuscense in the comments. 👇 #DataViz #Analytics #Robotics
-
??? 💡???
We have an incredible special guest that's joining the #Actuate2024 speaker line up. We'll be announcing them on Tuesday August 13. The first person to guess who the incredible guest speaker is before August 13 will get 2 FREE tickets to Actuate. Get tickets here: https://lu.ma/actuate Repost with your guess or put your guess in the comments.
-
🚨 New speaker announcement: Jason Sprowl, Principal Software Engineer, Agility Robotics is part of the #Actuate2024 speaker lineup! 👋 Welcome, Jason! You and Ryan Cook are going to be a fantastic duo on September 18. Get your tickets today and come see Jason live at Actuate! 👉 https://buff.ly/3Rnfteb 🎟️
-
🚨 New speaker announcement: Ryan Cook, Director of Engineering, Agility Robotics is part of the #Actuate2024 speaker lineup! 👋 Welcome, Ryan! You and Jason Sprowl are going to be a fantastic duo on September 18. Get your tickets today and come see Ryan live at Actuate! 👉 https://buff.ly/3Rnfteb 🎟️
-
We have an incredible special guest that's joining the #Actuate2024 speaker line up. We'll be announcing them on Tuesday August 13. The first person to guess who the incredible guest speaker is before August 13 will get 2 FREE tickets to Actuate. Get tickets here: https://lu.ma/actuate Repost with your guess or put your guess in the comments.
-
“To simplify deployment and debugging, the ROS 2 core team has spent a good part of the last year integrating Zenoh into ROS 2.” We're incredibly excited to listen to everything Chris has to stay, live at #Actuate2024. Get your tickets today to listen to and meet Chris live 👉 https://buff.ly/3Rnfteb
-
“Our process took weeks, now it takes minutes using Foxglove”. Brandon Minor, CEO, Tangram Vision Check out the Foxglove + Tangram case study to learn more. 💜 Link in the comments 👇