Today, we’re announcing updates that build on this foundation. We’ve added new capabilities that enable you to do more with Spot. We’re making it easier to manage missions and data. And we’re constantly improving hardware and systems to best meet the demands of dynamic, complex facilities.

• Acoustic vibration sensing
• Reality capture
• Orbit updates
• Mobility improvements
• And hardware upgrades.

Check out everything new with Spot and Orbit!

The post Introducing Acoustic Vibration Detection & More appeared first on Boston Dynamics.

This week we announced the retirement of our hydraulic Atlas and unveiled what comes next—a fully electric Atlas robot designed for real-world applications. The next generation of the Atlas program builds on decades of research and furthers our commitment to delivering the most capable, useful mobile robots solving the toughest challenges in industry today: with Spot, with Stretch, and now with Atlas.

The post Introducing Electric Atlas appeared first on Boston Dynamics.

Orbit is your portal for managing asset-intensive facilities through real-time and predictive intelligence. An evolution of our software offering, Orbit brings a whole new suite of fleet management capabilities and will unify your ecosystem of Boston Dynamics robots, starting with Spot.

The post Introducing Orbit Fleet Management Software appeared first on Boston Dynamics.

Today we announce a major advancement in unloading speed: Stretch will pick and place multiple boxes— currently up to four at once—with a feature we are calling multipick. Containers are often filled with thousands of boxes, so enabling Stretch to move multiple boxes instead of one with a single swing of the arm results in significantly higher productivity.

The post Introducing Multipick for Automated Unloading appeared first on Boston Dynamics.

Spot moves from asset to asset across a facility to get real-time information on equipment including pumps, motors, compressors, and more, so plant managers can improve uptime while decreasing costs of downtime and maintenance. With our newest software release, Spot Release 3.2, we’ve made enterprise asset management easier than ever. This release adds built-in data processing and review, improvements to the data collection pipeline, and a better operator experience.

Built-in Data Processing and Review

In addition to offering tie-ins to third party data processors, we now offer out-of-the-box processing capabilities for thermal inspections, as well as data plugins through our Scout API. 

Thermal Imaging – Collection and Analysis

With the Spot CAM+IR, Spot users can perform detailed thermal inspections during routine autonomous missions. Our new thermal inspection capabilities allow operators to get more data on the health of their assets, see results and trigger alerts when assets go out of bounds, and see data trendlines on Scout. New tablet controls allow users to set minimum or maximum temperatures on regions of interest, triggering an alarm through Scout if breached. Users can also adjust span and level and adjust the colormap of thermal images.

Thermal data and trends are then easy to review and manage in Scout and users can select email or mobile alerts when equipment goes out of set bounds. These new data processing features will be key to enabling users’ asset maintenance programs.

Scout API

In addition to providing thermal data processing in Scout, for the first time ever we are releasing a Scout API. The Scout web API allows customers, developers, and integration partners to access data from any Autowalk mission or manual operation session run through Scout. This new API provides methods for querying the data collected by a site’s Spot fleet over time. It can be used to filter and sort results by a number of fields, including mission name, robot name, time, and mission result. These querying capabilities of the API can be leveraged to create targeted reports, such as reports on specific assets. Customers can also use the API to export data from Scout to another system, such as their preferred enterprise asset management system, in order to further integrate Spot into their data workflow.

Improved Data Collection

Not only have we added data processing with Release 3.2, but we’ve also made data collection with Spot easier through some new autonomy features. 

Arm Inspections

The Spot Arm gripper camera is now available as an additional inspection tool. The arm and its 4k camera can help users get a better look at inspection points that are higher up or hidden behind other objects. Arm inspections can be performed manually or as part of an autonomous mission.

Area Callbacks

We’ve added the option to trigger an action when Spot walks through specified areas on its mission map. In areas where certain checks or actions must be performed for the robot to navigate safely, Area Callbacks provide a new option to ensure actions are always performed at the correct place during autonomous navigation. The action will be performed in the area regardless of the actual sequence of events that caused the robot to end up traveling that route (normal operation, rerouting due to a blocked path, returning to a dock to charge the battery, etc.). Area Callbacks can trigger actions such as waiting at a factory crosswalk until it’s safe to cross, flashing lights or playing sounds, and more. 

Strict Path Following

Users can now set Spot Autowalk missions to use strict path following mode. When this mode is active, the robot will follow the recorded path closely during Autowalk replay and will not deviate from the path to walk around obstacles. This mode is for customers who want Spot to stay within a tightly constrained path, such as a pedestrian walkway in a factory that also includes vehicle traffic (e.g. forklifts) or other hazards. This mode is also intended for customers operating Spot in an environment—for example, a nuclear power plant—where deviating from the path could present safety risks.

Ground Clutter Avoidance

Ground clutter avoidance is an optional feature that restricts Spot from stepping on or over new objects or people on the ground during mission playback. This feature is designed for sites where sensitive equipment may appear on Spot’s inspection route.

Enhanced Operator Experience

Operating Spot and getting support should be easy. In this release, we’ve added automatic stairs registration and refined our support systems for logs and licenses. 

Automatic Stairs Mode

Spot can now automatically detect stairs and switch itself into stair mode during both manual operation and Autowalk. Operators will no longer need to manually switch the robot into stairs mode.

Connected Logging and Licensing

When Spot detects an issue, the robot logs data on its performance. With 3.2, customers can identify and directly upload small event logs to Boston Dynamics for faster and more streamlined support and assistance. The updated system includes:

• Smaller log file sizes for easier handling and faster transfer
• One single log file for each issue the robot encounters
• Optional direct upload to Boston Dynamics 

A network-connected Spot can also fetch its annual license. 

We’re excited to see our customers put these features to use in the field, inspecting and managing assets with Spot. For more information on new features in this release, please read the full release notes. Customers can update to release 3.2 now via the Support Center.

If you’re ready to get started with Spot, contact sales or join our upcoming thermal inspection webinar to learn more!

The post Spot 3.2: From Data Collection to Data Insights appeared first on Boston Dynamics.

We’ve been working closely with Spot users in asset-intensive industries to operationalize the robot on their sites. With Spot Release 3.0, we’ve added flexible autonomy and repeatable data capture, making Spot the data collection solution you need to make inspection rounds safer and more efficient. 

Every step of setting up Spot’s automated inspections has been streamlined for effective data capture and processing. Schedule missions for Spot to collect photos, thermal images, point clouds, and other critical data; process that data into valuable signals at the edge with computer vision models; and create custom uploads to send those signals to your existing systems, so it’s easy to keep all of your data in one place for analysis and review. Spot Release 3.0 makes dynamic sensing available to everyone. Here’s a detailed look at what’s new.

Flexible autonomy

Spot’s Autowalk system has logged thousands of miles in industrial facilities and on construction sites around the world. Release 3.0 adds powerful new capabilities to Autowalk, enabling operators to record autonomous missions that implement dynamic sensing sitewide.

• Mission editing: Map your entire site by extending paths and adding new inspection Actions to existing missions over multiple recording sessions.
• Mission planning: Save time by selecting which inspection Actions you want Spot to perform, and it will take the shortest path to collect your data.
• Dynamic replanning: Don’t miss inspections due to changes on site. Spot will replan around blocked paths to make sure you get the data you need.
• Scheduled missions: Inspect your site after hours with simple scheduling tools and hands-free, unsupervised autonomy.

DATA COLLECTION WITH AI AT THE EDGE

Release 3.0 makes data capture more reliable and easier to process. Now you can connect computer vision models to Spot, adding valuable context to teleoperation and turning raw mission data into actionable signals at the edge.

• Repeatable image capture: Capture the same image from the same angle every time with scene-based camera alignment for the Spot CAM+ pan-tilt-zoom (PTZ) camera. 
• Live review of computer vision models: Use TensorFlow models from our software partners or implement your own computer vision model to carry out inspection tasks such as gauge reading and thermal analysis. Preview computer vision models on the tablet and create smart Actions that process images within Autowalk.

ENTERPRISE INTEGRATIONS

Spot closes the loop with the systems you already use to understand and manage your operations, helping your team manage assets, detect anomalies sooner, track work, build digital twins, and more.

• Upload data: Automatically push data into your existing systems at the end of a mission with custom code.
• Cloud-compatible: Connect Spot to AWS, Azure, IBM Maximo, and other systems with existing or easy-to-build integrations.
• Scout: Use Boston Dynamics’ web-based remote operation application to manage your entire dynamic sensing fleet, schedule missions, and review data collected on site.

ADDITIONAL NEW FEATURES

Release 3.0 contains dozens of other features designed to help your team operationalize Spot and enable dynamic sensing on your site.

• Payloads: Remotely restart payloads, easily configure payload parameters, and more.
• Manipulation: Remotely operate the Spot Arm with ease through rear Spot CAM integration and split-screen view. Arm improvements also include added functionality for push-bar doors, revamped grasping UX, and updated SDK.
• Sounds: Keep trained bystanders aware of Spot with configurable warning sounds.

Ready to put Spot 3.0 to work on your sites?

Start your journey with Spot or update your robot today.

The post Spot 3.0: Flexible Autonomy & Repeatable Data Capture appeared first on Boston Dynamics.

Spot Release 2.1 acts on those insights and makes it easy for you to attach your own sensors, collect and save the data you care about, and integrate that data into your existing systems. With 2.1, we’re launching several features which make Spot immediately useful out of the box for autonomous data collection missions. These can be used by operations teams to repeatedly collect vital data in dangerous or remote sites.
 

NEW IN THIS RELEASE:

• Easily automate image collection workflows and aim the PTZ camera in Autowalk to get detailed inspection photos, autonomously.
• Put your data in-context with user-defined origins and custom metadata.
• Download mission data to the tablet for easy integration into third party tools.

EASY SENSOR INTEGRATION

Attaching new image sensors, like off-the-shelf spherical or thermal cameras, is now as easy as editing an example script and installing its docker container onto the Spot CORE compute payload. The new image sources show up on Spot’s tablet controller, and users can trigger captures in both teloperation and the easy-to-use Autowalk autonomy system. Spot can now be used to collect training images for computer vision models, to visualize data and model output live on the tablet controller, and to capture data from custom non-visual sensors like gas detectors or laser scanners.

COMPREHENSIVE DATA

Spot now has the ability to attach metadata to images, associating them with the robot’s location, user-defined labels, or custom values such as GPS coordinates from an attached payload. This enables users to put their data in context, for example: combining site photos from multiple missions into a single view, sorting images by asset-ID, or collecting datasets for computer vision model training. We’ve doubled-down on standard data types (JPEG images, JSON and CSV metadata files) to eliminate integration bottlenecks and built a high-performance system for developers to write their own data streams into the robot’s logs.

IMPROVED WORKFLOWS

Powerful tools aren’t powerful if operators can’t use them in the field, so we’ve streamlined the data collection workflow significantly. Users can capture data manually and autonomously in Autowalk and download it to the tablet’s SD card for easy off-robot use. Common actions and callbacks can be configured on the tablet for quick use during operation. We’ve also made numerous under-the-hood improvements to Spot’s industry-leading locomotion and autonomy, further enabling operators to focus on the job and not the robot.

SUMMARY OF NEW FEATURES

IMPROVED DATA COLLECTION DURING TELEOPERATION AND AUTOWALK MISSIONS

• Capture images from robot cameras, Spot CAM, and third-party image sources, tag them with metadata, and download them to the tablet for easy viewing and sharing.
• When recording Autowalk missions on the tablet, point Spot at items of interest and view image data in real-time.
• Annotate image data with robot position or custom metadata from easy-to-write data acquisition (DAQ) plugins.
• Export data in standard types for easy importation into off-the-shelf analysis tools.

ENHANCED ROBOT BEHAVIORS

• Improved obstacle avoidance, slip handling and recovery, stairs performance, self-righting on sloped terrain and near obstacles, crawl stability, and stability standing up with payloads and on sloped terrain.
• New roll-over behavior for easier access to the battery compartment.
• Improved fiducial position measurements and multi-fiducial support in GraphNav maps.

SPOT CORE AND CORE AI PRE-CONFIGURED SOFTWARE IMPROVEMENT

• Remote desktop support via TigerVNC.
• Cockpit provides a graphical system administration interface.
• Docker and Portainer enable deployment and management of Docker containers as components using a simple web UI.
• Pre-configured network settings provide better support for WiFi dongles.

ON-ROBOT LOG ACCESS FOR DEVELOPERS

• To assist with debugging, application developers using Spot can now access some logs stored on the robot, including:
  • Logs of API requests and response messages.
  • Text log messages and binary data.
• Developers can now contribute their own data to the on-robot log.

EASIER SYSTEM ADMINISTRATION

• Spot now collects logs from batteries, clears them, and includes battery log data in the system log bundle.
• Admin Console now provides a UI for rebalancing an imbalanced battery.
• Spot can now associate with 802.1x enterprise WiFi networks, including those which require certificates.

These new features in Release 2.1 unlock Spot’s full data collection potential and set the stage for exciting new capabilities coming early next year: self-charging and remote operation. Upgrade to 2.1 today or contact sales to put Spot’s game-changing technology to work quickly and reliably, right out of the box.

The post Spot Release 2.1 appeared first on Boston Dynamics.

Here’s a detailed look at what’s new and improved:

Autonomous Navigation APIs

• GraphNav API: Spot’s ability to perform autonomous navigation such as patrols and inspections has been dramatically expanded. In version 1.x, this capability was a tablet-only feature known as Autowalk, but in the 2.0 release, developers have access to the high-level autonomous navigation behavior behind Autowalk. Applications can now issue Spot high-level navigation commands such as “go to a waypoint” and track where the robot is located on a larger map. Developers can also record, edit, and upload maps to the robot.
• Missions API: This API provides a behavior tree-based system for programming autonomous actions. The Missions API works with the GraphNav API to allow users to fully integrate Spot with code for custom sensors and command sources.

Mobility

• Improved stair reliability, including on open risers and grated stairs.
• Improved performance on slippery surfaces.

Payloads

• Payloads can now use the Spot API to automatically inform the robot of their physical properties and the services hosted onboard. This enables external development of self-registering payloads that do not require any installation configuration beyond being attached to the robot.
• Spot CAM: A featured payload enabling improved situational awareness. Includes a 360° spherical color camera and an optional PTZ (Pan-Tilt-Zoom) camera or LIDAR to significantly enhance perception range for autonomous operation and data capture. Release 2.0 adds API access to the Spot CAM.
• Spot CORE: A ready-to-use on-board computer solution that provides users compute power on robot. Comes with Ubuntu and the Spot SDK, but users can reconfigure any way they want.
• Spot GXP: A lightweight power and networking solution for users looking to integrate their own payloads. Provides regulated power with current protection and a standard ethernet port.

Platform

• Added support for mDNS makes it easier to find robots on your network and reduces the overhead of maintaining host files and DNS entries.
• Robot communications revamped to provide more responsive connection over channels with significant interference or packet loss.
• Improved safe stop behavior. When the user cuts power, Spot will drop to the ground in a more controlled manner.

Other Expanded Developer Capabilities

• WorldObject and LocalGrid APIs: Users can access more of the information Spot senses. The WorldObject API shows objects discovered in the world such as fiducials. The LocalGrid API shows navigation information near Spot, such as terrain height.
• New Programming Examples and Documentation: The updated Spot SDK greatly expands the documentation and programming examples to help users learn how to develop on Spot.

Existing customers can download the release now by following instructions in the latest support email. Interested parties can check out our website for more information on the robot, available payloads, our updated developer platform, and current applications.

To learn more about Spot, please fill out our sales form.

The post Spot 2.0: Autonomy & Mobility appeared first on Boston Dynamics.

We developed the payload, hardware, and software for this application so that they are generalizable and able to be deployed on other mobile robotic platforms with APIs and capacity for custom payloads.

Today, we are sharing the results of our initial work deploying the robot with Bringham and Women’s Hospital in Massachusetts and we are open-sourcing the hardware and software designs used to get these robots into the field. Our hope is that these tools can enable developers and roboticists to rapidly deploy robots in order to reduce risks to medical staff.

APPLICATION DEVELOPMENT ON SPOT

Starting in early March, Boston Dynamics started receiving inquiries from hospitals asking if our robots could help minimize their staff’s exposure to COVID-19. One of the hospitals that we spoke to shared that, within a week, a sixth of their staff had contracted COVID-19 and that they were looking into using robots to take more of their staff out of range of the novel virus.

Based on these conversations, as well as the global shortage of critical personal protective equipment (PPE), we have spent the past several weeks trying to better understand hospital requirements to develop a mobile robotics solution with our robot, Spot. The result is a legged robot application that can be deployed to support frontline staff responding to the pandemic in ad-hoc environments such as triage tents and parking lots.

Today marks the second week of Spot’s presence at a local Boston facility, Brigham and Women’s Hospital, where the medical team uses the robot as a mobile telemedicine platform, allowing healthcare providers to remotely triage patients. We’re listening to their feedback on how Spot can do more but are encouraged by reports that using the robot has helped their nursing staff minimize time exposed to potentially contagious patients.

OPEN-SOURCE HEALTHCARE ROBOTICS TOOLKIT

With the deployment of our first healthcare-focused robot, we’re open-sourcing all of our work to empower mobile robotics platforms to leverage the same hardware and software stack that we’ve developed to help frontline healthcare workers. Below you’ll find an overview of how we are using (and plan to use) mobile robots to combat the spread of COVID-19.

None of the services below are reliant on Boston Dynamics hardware or software. In many instances, we imagine wheeled or tracked robots may be a better solution for these applications.

Specifically, we have already been in close contact with Canadian field robotics firm Clearpath Robotics, and their CTO Ryan Gariepy has affirmed that they too are actively working to assist robotics developers and researchers around the world in their efforts to support our healthcare workers and maintain our critical infrastructure. He further noted that this crisis serves to underscore that in the end, it is the application that should be front and center, and users should not have to care about the details of robot mobility.

For more information, including detailed documentation and files of CAD mounts and IRB applications, click here. If you’d like to work with us or are interested in using these robots on your site, please fill out the contact form at the bottom of the page. We will continue to update this page and the resources on our GitHub as developments are made.

WHAT WE’RE DOING NOW: TELEMEDICINE

With current protocols at local hospitals, patients suspected to have COVID-19 are asked to line up in tents outside to answer questions and get initial assessments for temperature. This process requires up to five medical staff, placing those individuals at high risk of contracting the virus. With the use of a mobile robot, hospitals are able to reduce the number of necessary medical staff at the scene and conserve their limited PPE supply.

Through an iPad and a two-way radio mounted on a robot’s back, healthcare providers can video conference with patients as they remotely direct the mobile robot through lines of sick individuals in the tents. With this configuration, doctors are able to speak with patients from afar, possibly even from their own homes. For every intake shift completed by a teleoperated robot shift, at least one healthcare provider is able to reduce their interaction with the disease.

WHAT WE HOPE TO DO NEXT: REMOTE VITAL INSPECTION

To further assist healthcare providers in triaging sick patients, the robot will need to support collecting additional vital sign information.

In order to provide this service, we need to figure out how to remotely measure:

• Body temperature
• Respiratory rate
• Pulse rate
• Oxygen saturation

We have been in dialogue with researchers who use thermal camera technology to measure body temperature and calculate respiratory rate. We’ve also applied externally-developed logic to externally-mounted RGB cameras to capture changes in blood vessel contraction to measure pulse rate. We are evaluating methods for measuring oxygen saturation.

WHAT WE HOPE TO DO NEXT: DISINFECTION

By attaching a UV-C light or other technology to the robot’s back, Spot could use the device to kill virus particles and disinfect surfaces in any unstructured space that needs support in decontamination – be it hospital tents or metro stations. We are still in the early stages of developing this solution but also see a number of existing mobile robotics providers who have implemented this technology specifically for hospitals.

We hope our fellow mobile robot providers, existing customers, and medical professionals will be able to use this information to leverage mobile robots to take people out of harm’s way during this critical time. Together, we can improve conditions for healthcare workers and essential personnel around the world, save lives, and fight COVID-19.

More details and reference designs will be made available as we complete testing and validation.

Click here to access our COVID-19 GitHub repo and learn more.

The post Boston Dynamics Covid-19 Response appeared first on Boston Dynamics.