Design and Development

Warehouse logistics and advanced manufacturing are increasingly using robotics as a critical part of their automation strategies. They can improve operational efficiency, improve safety, and help companies address the persistent labor shortages that are being observed across the globe. Developing these intelligent robotic 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 processes.

This talk will describe the many ways NVIDIA Isaac Sim can be used to accelerate the development and deployment of robots, including advanced AI and computer vision. Specifically, attendees will learn how simulation can test robot applications in photo-realistic, physically accurate digital twin environments. In addition, the robots can be placed in increasingly complex simulations involving digital humans and fleets of robots to optimize operational KPIs. This session is designed as an introduction to photo-realistic 3D simulation for robots and is appropriate for all levels.

With the rapid acceleration of robot deployments, the need for heterogeneous fleet management will become standard. In this session, Intrinsic will share recent developments in the Open-RMF platform and present use cases where it has been deployed. Intrinsic will also present a roadmap about the future of Open-RMF and interoperability and some of its latest tools and capabilities, including:

– Multi-agent planning framework – Mapf is a library for cooperative path finding
– Task Management – the latest improvements including a flexible task framework to allow custom task definitions, multi-phase tasks, prioritization and more
– Site Editor – a desktop or web utility to visualize and edit large deployment sites

– Crowd Simulation – a plugin to simulate human actors with multiple behaviors
– Obstacle Detectors – packages that infer the presence of obstacles from sensor inputs including LIDAR or 2D/3D cameras

Vegetable farming still relies on labor-intensive processes. Weed control in particular, which is critical to ensure good yields, is mostly taken care of by hand crews who walk the field with hoes. After prototyping for 5 years in the epicenter of lettuce production in North America, FarmWise is about to release its first commercial robotic weeder. This machine can detect crops from weeds and mechanically uproot the undesired plants with extreme precision using deep learning and actuation control. This talk will walk you through the team’s journey and learnings from the first demo to the architectural decisions behind their new product.

Spot, Boston Dynamics’ quadrupedal robot, can reliably walk nearly anywhere a human can, but what does it do? While legged mobility is necessary for many use cases, it’s not the only requirement for value-producing applications. This talk will focus on the work we have done to develop Spot for remote and autonomous sensing applications:
– Encapsulating Spot’s mobility in an extensible API
– Building an autonomous capability
– Making it easy to add sensing to build value-producing solutions

New hardware, sensors, algorithms, and AI technologies have opened up the ability to rethink how robots are developed for use in unstructured environments. Using a first principles approach, Apptronik has used the same platform to develop a range of robots from exoskeletons to humanoids. This has resulted in reactive, compliant, lightweight, and affordable robots that can perform a variety of tasks in existing human environments. In this session, you will about Apptronik’s approach to developing a platform for general-purpose robots, their use cases, and the future viability of these systems

From vacuums to quadrupeds to self-driving cars, robots are becoming increasingly physically capable, intelligent and cost-effective. As with any emerging industry, the earliest innovators didn’t have the luxury of decades of fundamental knowledge and best practices available to them. They built from the ground up and learned the hard way what not to do.

Today, we’re entering a new era of robotics. The most successful robotics companies of the next decade won’t be the ones building from scratch. They’ll build on existing platforms that have been hardened to solve very specific problems, including problems in autonomy, fleet management, simulation, and more throughout the robotics stack.

In this presentation, the audience will learn how robotics development has been done
recently, what is changing, and what is coming in the next decade from an expert with
fifteen years of experience in robot development and deployment across a variety of
industries. Market expectations surrounding robotic capabilities, security and privacy,
and robustness and safety are becoming increasingly difficult for new entrants to match.
Nevertheless, a variety of market forces are making building robots cheaper and easier
than ever before, and demand for robotics has never been higher!

Just as a new software company today wouldn’t build its own cloud computing
platform, and instead would use AWS, the next generation of robotics companies are
not going to start with a hodgepodge of ROS nodes and custom circuit boards. It is
highly likely that some of the world’s largest robotics companies haven’t even been
founded yet!

The robotics industry is at an inflection point because software advancements can offer a full paradigm shift in how to scale a successful robotics business. At MongoDB, Horowitz’s data platform was the foundation for dozens of $1B+ high-growth software companies. That same style of software infrastructure advancement is now coming to robotics to support a wave of high-growth robotics companies.

In this session, Viam and MongoDB co-founder Eliot Horowitz will detail why this is the best time to launch a robotics business and how a modern approach to software can get you from paper to prototype to production to successful, scaled business faster than ever.