May 10, 2023

Commercial depth sensors have been a tremendous asset to kick-starting and developing robot platforms; however, off-the-shelf sensing can constrain your project through a variety of means. Whether it is the software integration that falls short or the initial hardware offering falls outside the scope of critical performance requirements, users often find themselves left wanting on a number of different axes. As a result, more robotics companies are choosing to “roll their own depth” by combining off-the-shelf components with available compute and software to create and maintain a depth stack that fits with the evolving needs of their platform. In this talk, we’ll cover what we’ve learned it takes to build depth, from optics and compute selection to industrial design considerations and software requirements.

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