Blog

3 Reasons Why Autonomous Vehicles Need to be Able to React Like a Human

Posted on by Erin

As the age of automation continues to gather steam, car manufacturers are racing to achieve the ultimate goal: full autonomy of vehicles. However, before this becomes a reality, there are many hurdles to navigate. As an earlier post outlined, rapid motion planning (RMP) is an essential component for autonomous vehicles (AVs) to realize their potential.

To date, motion planning software has been constrained by general-purpose hardware. Here at Realtime Robotics, our RMP incorporates both specialized software along with, for the first time, dedicated hardware for motion planning, allowing the performance to be transformed.

So what are the benefits of rapid motion planning?

1. Speed it matters

Our technology supercharges response rates. For example, at 35mph, a car with RMP can react after traveling only half a foot.  (The car travels 1 foot every 20msec.) Compare this with traditional motion planning software where the same vehicle requires 100msec to generate a plan, meaning it can only react after traveling 5 feet. This ability to respond quickly is transformative as it allows more time to react and respond to risks, thus increasing safety.

2. Risk-aware planning

RMP can compute multiple possible behaviors of the other agents in the environment, such as cars, bikes, and pedestrians, all within the desired reaction time of 10msec. Before this, motion plans relied on a sole plan at each planning interval and hoped it was good. As a result of this, in urban environments where there is more uncertainty, the cars drive very slowly. RMP generates multiple scenarios simultaneously and creates the best plan within the defined risk tolerance.

3. Power play

Power usage is another key advantage as our technology uses significantly less power than motion planning utilizing general-purpose hardware. Hardware designed for a specific application is always more efficient than general-purpose hardware.

Our RMP supercharges the ability of AVs to recognize and respond to unforeseen events that will help deliver a new age of smart automation. For example, it’s able to accommodate a bicyclist who veers out of the bike lane and the pedestrian who suddenly steps off the sidewalk into the road. RMP enables AVs to react like a human without incurring any of the human’s flaws, such as being distracted by the radio or driving when tired.

The three key benefits outlined above will rapidly accelerate the reality of fully autonomous vehicles navigating urban environments. So, in a nutshell, risk-aware, rapid motion planning is the future of AVs.

Share on: Twitter | Facebook | LinkedIn

The Future of Robotic Automation in the 2020s

Posted on by Erin

The new decade is now upon us and media, academics, and analysts are buzzing with predictions for what we can expect from automation in the coming years. At Realtime, we believe that robotic automation will move from vision to reality. In the 2020s and beyond, I think we’ll see robots become part of our lives in ways we couldn’t have imagined. Here are four predictions that we can expect to see come to fruition throughout this decade.

Robots as we know them have peaked

Demand for power and forced limited robots (cobots) has peaked due to reduced functionality and capabilities. By 2025 manufacturers will no longer be investing in these systems, and traditional cobots will be replaced by better technology for the human-robot workcell.

Slashing the programming burden will drive the adoption of industrial robots

Industrial robots will become more pervasive as they will become significantly easier to program. As robotic automation expands into new industrial areas like logistics and electronic assembly, this will be essential to facilitate widespread adoption. The shift in programming from script-based to graphical-based will be the catalyst behind this.

The regulatory environment will slow down the pace of progress

In the 2020s, the AI and ML technology landscape will move from the ‘Wild West’ where almost anything goes to a more controlled regulatory environment. The introduction of mandatory legislation will inevitably slow down the pace of progress, and this will impact robotic automation. For example, AI and ML algorithms will face safety regulations, and this will hamper the speed of development of vision systems that are the key to autonomous vehicles along with industrial robots taking on more complex tasks such as kitting or parcel sorting.

Robots will look very different, but functionality will remain limited

Human service robots will become much more prevalent; however, they will look completely different. Robots will transform to resemble small, cute pets so that they are less threatening to people. However, despite looking very different, they will still be relatively limited in terms of functionality. Despite the array of personal robots unveiled at CES, the days of robots being the answer to the grind of household chores is a long way in the future, so for now, people will still have to fold their laundry!

Robotic automation will be a crucial driver behind Industry 4.0 in the coming years, with robots ultimately becoming commonplace in both the workplace and homes. There will be some hurdles to overcome but it’s clear that the reliance on robotic automation will continue to grow as the decade progresses.

Share on: Twitter | Facebook | Linkedin

Smart Robots Starring Realtime Robotics at iREX2019

Posted on by Erin

Every December, the robotics industry gathers in Japan to showcase the latest innovations at iREX, the world’s largest robotics trade show.  At the event, we were excited to unveil for the first time, Realtime’s technology integrated with various partner’s robotic systems.

For those who were not able to make it to Japan, then check out the videos below, showing how we are making smart collision-free autonomous motion planning a reality, removing many of the boundaries to broader robotic automation.

Mitsubishi Electric with Realtime Robotics

First up is our smart motion planning technology embedded into Mitsubishi Electric’s industrial and collaborative robots.

https://www.youtube.com/embed/bhGOD0Z3hvo

JOHNAN and Realtime Robotics

Working with our partner JOHNAN, we were able to integrate our technology with Yutaka’s robots to demonstrate collision avoidance.

https://www.youtube.com/embed/RHGICUdUDfI

Nachi and Realtime Robotics

Finally, a video of our hardware and software running a Nachi picking application.

https://www.youtube.com/embed/xQKSWckLL1I

Realtime’s innovative motion planning technology empowers end-users to transform industrial automation. To find out more about how to deploy collaborative workcells without compromise for your application, reach out to us here:

Share on: Twitter | Facebook | Linkedin

Five Career Questions With Our CEO

Posted on by Erin

Although Peter has been traversing the globe meeting with customers, partners, and prospects, we managed to track him down to answer five questions on how to prepare for a career in a robotic automation company.

Peter Howard

What do you wish you had known at the start of your career in robotics?

How primitive robotics really was and how long it would take to overcome fundamental limitations in basic technologies like motion planning…  And that it would take the promise of autonomous vehicles to finally attract enough money to propel robotics to the next level.

What’s something that you didn’t learn at college?

The difference between making a proof of concept that works once, and a commercially viable product that always works. The academic world typically doesn’t prepare you for this challenge!

What skills should kids develop to be successful in our new, automated world?

Focus on working in groups on school projects and helping everyone to contribute. Also, play as much as possible to hone your creative problem-solving skills.

What do I wish I could tell my 21-year-old self?

Trust your instincts, but use your head.

How did you end up as CEO?

Based on a repeated track record of building teams of capable, dynamic people who continuously develop and realize visions for how technologies can change industries in positive and profitable ways.

Share on: Twitter | Facebook | LinkedIn

Mitsubishi Electric and Realtime Robotics Bringing Motion Planning to Life

Posted on by Erin

Rather than telling you about our amazing technology, we wanted to share a video with our partner and investor, Mitsubishi Electric. The video below shines a spotlight on how we are enabling multi-robot workcells to operate safely at a productive pace.

With Realtime’s software and hardware embedded into the Mitsubishi Electric robots, they can now see and avoid any obstacles. The robots are smart enough to adjust or stop their motion if necessary, without any additional programming required.

Check it out for yourself!

https://youtu.be/ygrMxdpLQEY

The video shows how robots can collaborate together quickly and precisely. If you want to find out more about how to increase throughput and simplify programming then contact us below.

Share on: Twitter | Facebook | Linkedin

Why Autonomous Vehicles are Stuck in Neutral

Posted on by Erin

Despite the surge in funding and news that autonomous vehicles (AVs) are attracting widespread adoption is still far from becoming a reality. To date, there has been a lot of success driving in relatively friendly conditions like highways in California. However, before AVs can be let loose in complex urban environments, they need to be much more competent, reliable, and safe!

The urban environment roadblocks

Unlike perfect highway driving conditions, AVs in an urban setting must drive within close proximity to other agents such as cars, bikes, and pedestrians, whose movements it does not control, and cannot completely predict in advance. An AV must be able to anticipate the potential future actions of other agents and preemptively maneuver to avoid collisions.

Cars-Swerving

Imagine a car driving at 25 miles an hour past a school that has just been let out for the day. The scene around it is filled with children of varying ages, many of them looking at their phones. If that car continued to drive straight at its current speed – which is the standard speed for urban roads – and only reacted when a child stepped onto the road, there is a high chance that it will be unable to stop in time. Similarly, any simple reactive reflex-like swerving may cause the car to hit another child on the sidewalk, or to swerve into the path of an oncoming vehicle. One safe alternative here is to assume the worst case: that all of the children could walk into the road at any minute; the right solution then is to halt the car in the middle of the street until all the children are gone, which is not practical.

AdobeStock 315443081-1

Instead, the car should sense the children, understand that there is a low but non-negligible probability that each of them may step into the road, and then proactively take action to avoid a collision by slowing down and creating some space between it and the sidewalk. This must happen before any of the children steps onto the road – afterward is already too late.

To do this requires the AV to model all the ways in which the agents around it may move, assign probability estimates to them, and then use those estimates to build a safe, proactive motion plan. But there are many agents, and many possible ways each of them can move, which makes the resulting problem very computationally challenging – even more so when safe operation requires the AV to plan several times a second, and react to unexpected events within 100ms. Existing software and GPU based motion planners can’t achieve this level of performance, and therefore can’t ensure an acceptable level of safety at normal driving speeds in urban environments.

The Realtime Factor

Here at Realtime, we have developed an AV motion planning processor that applies our deep technical expertise in designing specialized hardware for motion planning – we build the fastest motion planning solutions – to this critical problem, resulting in a power and cost-efficient motion planning unit capable of both proactive risk-preemption, and high-speed reactive response.

By leveraging precomputation, circuit-level parallelism, and high-speed specialized motion planning circuitry, we provide an innovative and unique solution. AVs with our technology can recognize and respond to unforeseen events, such as a pedestrian who suddenly steps off the sidewalk into the road. Another key advantage is that AVs are now able to react like a human without incurring any of our human failings, such as checking our phone while driving.

If fully autonomous vehicles are to become a reality in dynamic urban environments, then solving the motion planning conundrum is an essential piece of the puzzle. To find out more about how we are helping AV manufacturers then reach out here:”

Share on: Twitter | Facebook | LinkedIn

Realtime Robotics Raises $11.7 Million Series A Funding

Posted on by Erin

Technology enables robots and autonomous vehicles to automatically plan and respond to changing environments

BOSTON (OCTOBER 16, 2019) – Realtime Robotics, the inventor of responsive motion planning for industrial robots and autonomous vehicles, announced today that it has raised $11.7 million in Series A funding. Led by SPARX Asset Management the round included participation from Mitsubishi Electric Corporation, Hyundai Motor Company, and OMRON Ventures, alongside existing investors Toyota AI Ventures, Scrum Ventures, and the Duke Angel Network. The new capital will be used to accelerate the development of more commercial product releases and expand the team to support key customers and partners across the globe.

The interest in the round reflects Realtime Robotics’ first-mover advantage in the market for solutions that eliminate the obstacles to widespread adoption of advanced automation in industrial, agriculture, food service, construction, healthcare, and consumer settings.

Despite the growing demand for automation, today’s robots are not safe or smart enough to navigate in dynamic, unstructured environments, without costly safeguards and oversight. Realtime Robotics’ solutions eliminate these challenges and enable robots to work at a productive pace. Its specialized computer processor and software enable machines, including industrial and collaborative robots and autonomous vehicles, to evaluate millions of alternative motion paths to avoid a collision and choose the optimal route before making a move, all in milliseconds. It released its first commercial solutions RapidPlan and RapidSense earlier this year and you can see the automatic planning technology in action:

Realtime Robotics was founded in 2016 by Duke University professors Dan Sorin, George Konidaris, and researchers Sean Murray and Will Floyd-Jones, based on groundbreaking DARPA-funded research in motion planning.

“The commitment garnered from strategic investors reflects both the need and the demand for smarter robots. Our technology transforms the way machines interact with both people and other machines.  Robots will now be able to take on a wide range of new tasks and manufacturers will finally benefit from the productivity and efficiency gains that increased automation has promised, but failed to deliver.”

— Peter Howard | CEO | Realtime Robotics

“Realtime Robotics’ technology is ground-breaking and will transform the deployment of robotic automation across a range of industries. We’re proud to work closely with the team as they begin to help their customers reduce the friction, cost, and complexity of automation.”

— Seiji Miyasaka | Head of US Investment Team | SPARX Asset Management Co., Ltd.

“We are excited to partner with Realtime Robotics to deliver the first fleet of robots that can work smartly and respond to changing environments on the fly. Our investment will accelerate the adoption of safe and productive robotic systems across the globe and will ensure that robots realize their potential in industrial settings and beyond.”

— Satoshi Takeda | Senior Deputy General Manager of Nagoya Works | Mitsubishi Electric

“Dynamic motion planning in real time for unstructured environments has been a long-standing problem in robotics. OMRON Ventures is proud to support Realtime Robotics, whose innovations can vastly improve the capability and applicability of industrial robots leading to the creation of new business opportunities in this area.”

— Tomoko Inoue | CEO | OMRON Ventures

About Realtime Robotics

Realtime Robotics has developed responsive motion planning solutions for industrial robots and autonomous vehicles. Its specialized processor generates safe robotic motion plans in milliseconds, enabling robots to function in unstructured, collaborative work-spaces, reacting to a dynamic world the instant changes are perceived. Its solutions expand the potential of automation. Learn more about Realtime Robotics here and connect on Twitter and LinkedIn.

Share on: Twitter | Facebook | LinkedIn

Realtime Robotics Unveils Realtime Controller

Posted on by Erin

Simplifies and reduces the programming burden, accelerating the integration of robots

Realtime Controller

The Realtime Controller

BOSTON (April 30, 2020) – Realtime Robotics, the inventor of responsive motion planning for industrial robots and autonomous vehicles, today announced the launch of its Realtime Controller. The solution dramatically reduces and simplifies the programming required to safely integrate robotic workcells, speeding up the time to deployment.

As the pressure intensifies to improve margins it will accelerate the adoption of robotic automation. However, integrating robotic operating systems currently is complex, time-consuming, and cost-prohibitive, which has limited where and how the technology is deployed. With the Realtime Controller, multi-robot cells are much more flexible, as it automates many core processes and can dynamically adjust to variable production conditions.

Using Realtime’s Controller, manufacturers can now quickly and easily plan, simulate, and validate automation through the entire deployment. The Realtime Controller connects with the customer’s PLC and robot controller so that they can autonomously calculate, communicate, and execute collision-free motions. Both development time and cycle time are significantly reduced with automated interlocks and interference zone-free multi-robot workcells enabling robots to be deployed more quickly and expand into new areas that were previously cost-prohibitive.

The Realtime Controller is an industrial hardware computing platform with proprietary hardware and software that supports both off-line programming and run-time operation of single and multi-robot work cells. The software toolkit and API enable easy integration with PLCs, picking systems, robot controllers, simulation software, and other task planning solutions. Its web-based interface allows companies to configure and monitor robot workcells, including visualizing robot motions and managing fault conditions. In addition, Realtime’s motion planning enables immediate and autonomous fault recovery solutions for multi-robot workcells.

The Realtime Controller will be commercially available in North America, Europe, Japan and China beginning in May 2020.

“Our vision is to reduce the friction associated with deploying robots in industrial settings. The Realtime Controller is a catalyst for accelerating and simplifying robotic automation across the globe, enabling manufacturers to finally benefit from the power of industrial robots working together.”

— Peter Howard, CEO, Realtime Robotics

“Realtime’s RapidPlan technology and the new Realtime Controller provides the power to transform how we deploy and operate industrial robots. The solution dramatically reduces time for motion planning and eliminates interlocking, so our engineers can focus their efforts on designing fully capable work-cells and efficient multi-robot deployments.”

— Gurpreet Ghataore, Advanced Research Engineer, The Manufacturing Technology Centre

Other Resources

Share on: Twitter | Facebook | LinkedIn

How Realtime Reduces the Friction Associated with Deploying Industrial Robots

Posted on by Erin

Instead of painstakingly programming each move and coordinating multiple robots to work together, Realtime takes command of the movement and coordination functions, autonomously moving single or multiple robots to their goals while avoiding both static and dynamic objects in the environment. The processor removes the need for manual iterative programming and a software toolkit allows users to intuitively work with the Realtime Controller to provide collision-free plans autonomously. This means you can expedite the entire deployment process — system engineering, motion planning, task deployment, and reprogramming — and combine them into a fully autonomous solution that saves you significant time and money while maximizing throughput.

Benefits for Manufacturers

With Realtime’s technology, manufacturers can transform the deployment of robotic automation.

  • Faster, easier robot programming with accelerated offline motion planning
  • Increased throughput with interlock-free multi-robot workcells
  • Flexible workcells with collision-free planning in real-time
  • Safely deploy industrial robots in shared workspaces typically reserved for collaborative solutions

If you are looking to transform how you program production cells and accelerate your automation implementation while maximizing flexibility, then Realtime’s innovative technology is the answer. Find out more about how Realtime is helping remove the friction associated with the deployment of multi-robot workcells in this white paper.

Share on: Twitter | Facebook | LinkedIn

Putting the Need for Interlocks in the Rearview Mirror

Posted on by Erin

If one robot is good, then more robots should be better. In theory, putting several robots in a workspace, with all of them working simultaneously, should greatly boost productivity. In practice, however, the marginal benefits of adding robots are slim. Why? Programming! Engineers must orchestrate all of the robot motions to achieve as much performance as possible while guaranteeing that there will never be any collisions. This is extremely difficult — just imagine if you had to “program” a restaurant’s kitchen, orchestrating all of the motions of several chefs.

Because the problem of avoiding collisions is so difficult, robot programmers fall back on a simple, but poor performing solution. They identify every region in the workspace that is reachable by more than one robot, and they refer to these regions as interference zones. They then use locks to ensure that only one robot may be in an interference zone at any time, thus guaranteeing that collisions cannot occur. This solution is easy, but misses many opportunities for robots to be safely moving within different parts of an interference zone.

With technology from Realtime Robotics, multiple robots can productively share a workspace, with no complicated programming or interference zones. Realtime’s solution just requires the user to provide a list of tasks and task priorities, and this can be done with a simple PLC program without the need for interference zones or orchestration of any kind. From there, Realtime’s motion planning technology automatically finds collision-free motion plans for every robot, significantly reducing deployment time and cost, and significantly improving the productivity of the workspace.

Share on: Twitter | Facebook | LinkedIn