Exploiting Technologies Track

Over the last 50 years, machines have changed dramatically, becoming more autonomous, intelligent and mobile than ever before. In short, today’s machines do more with less human supervision. They’re also increasingly connected, both to the Internet and to other machines and devices.

In light of these changes, society needs to reevaluate our understanding of what it means to safely deploy machines, especially in scenarios where they will work closely with people. The safety measures of the past, when machines were bolted down, caged, or controlled by wired systems, are not suited for the age of autonomy. Robotics systems and smart machines need a new approach to safety— one that includes cybersecurity as a primary consideration.
In this session, FORT CTO Nathan Bivans will discuss:

– The convergence of IT and OT
– Cybersecurity threats in OT environments
– Best practices for mitigating safety and security risks

Commercial robotic systems typically require multiple types of sensors to capture information about the physical world, which following fusion and further processing allows them to orient themselves, avoid obstacles, navigate, and provide additional information. The number, type, and quality of the onboard sensors vary depending on the price and target application for the platform. Common sensor types include 2D / 3D imaging sensors (cameras), 1D and 2D laser rangefinders, 2D and 3D sonar sensors, 3D High-Definition LiDAR, accelerometers, GPS and more. Thankfully, solution providers continue to release low-cost, increasingly powerful products, and new sensing technologies are always emerging. In this panel session, attendees will learn of the latest advances in sensing products and technologies, including use cases highlighting important trends and examples of the latest sensing trends and techniques.

AI, including machine learning and deep ;earning, is increasingly impacting our personal lives, and the use of AI-powered robots in manufacturing facilities, power plants, warehouses, and other industrial sites also continues to expand. Warehouse bin-picking provides just one example. In an e-commerce fulfillment warehouse, human workers need to pick and place millions of different products into boxes based on customer requirements. Deep learning and reinforcement learning now enables robots to learn to handle various objects with minimum help from humans. In this session, YJ Lim, Senior Technical Product Manager of Robotics and Autonomous Systems at MathWorks, will describe how to empower robotics systems using deep learning and reinforcement learning for perception and motion control in autonomous robotics applications including robot manipulators, autonomous mobile robots, and UAVs.

Companies in the commercial and industrial sectors are increasingly turning to robotics automation reduce costs, improve productivity, and increase operational efficiency. Companies in the consumer sector, too, have turned to robotics technologies to drive their businesses, releasing new products and robotizing existing offerings. Developing these systems, however, is a complex, challenging, and costly undertaking. Thankfully, advanced simulation tools are available to engineers that can speed the design, development, and testing of robotics systems.

In this session, NVIDIA’s Erin Rapacki-Bishop will describe the many ways simulation platforms can be used to accelerate the development and deployment of intelligent robotics systems. Specifically, she will describe how simulation can be used to test robot code in photo-realistic, physically accurate environments, as well as model behaviors inside a simulated worksite to ensure the robot performs efficiently within the process flow of a real-world facility. This session is designed as an introduction to photo-realistic 3D simulation for robotics and is appropriate for all levels.

In addition to automotive applications, 3D LiDAR data can be leveraged for many other use cases. Examples include robotics systems, vehicle and pedestrian flow monitoring, security and industrial applications. However, effectively using LiDAR data in real-time is a complex, expensive, and long endeavor even for the expert 3D engineers. The lack of any standards makes it also even more challenging and threatens to slow down market adoption of powerful 3D LiDAR solutions. In this presentation, Raul Bravo, President of Outsight, will demonstrate how application developers and integrators can seamlessly use of LiDAR data from any hardware supplier. Specific use cases and real-life LiDAR recordings will be used to illustrate the practical applications.

Common wireless connectivity challenges for robotics automation include disconnects while autonomous mobile robots (AMR) roam between indoor wireless access points, lack of coverage in very large outdoor areas for automated guided vehicles (AGVs), and inconsistent latency in network communications. These challenges force many enterprises to stick with wired LAN connectivity in order to ensure predictable quality in network communications for their robotics infrastructure – limiting their ability to support robotics use cases supported with mobility and incurring high costs due to large investment in cabling costs.
All of these challenges can be addressed with private 5G LANs, at a fraction of the cost compared to these traditional options. In this session, Mehmet Yavuz, CTO of Celona, will discuss how leaders in the supply chain industry can craft their own private cellular strategy given their existing infrastructure, unique environments and desired business outcomes. Topics include:

– Introduction to Use of Private LTE/5G Cellular in the Enterprise

– Common Customer Use Cases and Technology Benefits
– 5G LAN Deployment Principles to Support Robotics Automation

– Onboarding Options to Private Cellular for Robotics Infrastructure
– Total Cost of Ownership and Return on Investment Analysis

This session will discuss some of the challenges facing robotics engineers to achieve leading edge performance and reliability, while navigating around tight design constraints. Power density continues to be a cornerstone in robot actuator design, but this is often compromised by additional functionality required of actuators and their cabling. We will examine how to improve performance while not only minimizing the weight of actuators but also the size of the control cabinet and simplifying cable routing requirements with integrated servo drives.

Any Internet search using the terms “artificial intelligence” (AI), “cognition”, or “machine learning”(ML) with the word “robotics” will return a slew of research and commercial initiatives focused on focused on robotic decision making, object identification, vision processing, autonomous navigation, motor control, sensor integration and other functions, as well as speech, facial and emotion recognition. Robotics designers and engineers are exploiting these capabilities to increase the efficiency and safety of their systems. They are also taking advantage of different types of distributed execution architectures – edge, fog and cloud – to optimize their systems and their intended applications.

In this panel session, attendees will learn how the latest AI and machine learning software and hardware technologies and techniques are currently being employed in robotics systems to make robots more intelligent and functional. Emerging capabilities and commercial opportunities will be highlighted.