\n Landshut. The BMW Group is expanding its expertise in
\n the field of physical AI, with BMW Group Plant Landshut taking on
\n central software development tasks for AI-supported robotics in
\n component production. The focus is on open software platforms, the
\n generation, provision and processing of training data, simulation and
\n motion planning, as well as the training of robotic systems. These
\n activities complement the pilot projects already underway exploring
\n the use of humanoid robotics at Plants Leipzig and Spartanburg.<\/p>\n
Landshut is leveraging its role as a centre of expertise for in-house
\n component production. The wide range of products and manufacturing
\n processes provides ideal conditions for developing and evaluating new
\n approaches using AI-supported robotics under real-world production
\n conditions. At the heart of these activities is the question of which
\n tasks will be suited to humanoid robotic systems in the future \u2013
\n particularly where flexibility, fine motor skills and an understanding
\n of the working environment are required. For this purpose, Plant
\n Landshut is developing software that enables robots to perceive their
\n environment, evaluate situations and derive appropriate actions independently.<\/p>\n
\u201cAt BMW Group Plant Landshut, we are combining software expertise
\n with industrial practice in our component production. This allows us
\n to test new technologies at an early stage and carefully evaluate
\n their benefits for production,\u201d says\u00a0Dr Wolfgang Bluemlhuber,
\n head of Driving Dynamics and In-house Component Manufacturing.<\/p>\n
\u00a0<\/p>\n
\n Technological foundations for AI-supported robotic systems
The starting point is further development of the software
\n architecture. At its Landshut facility, the BMW Group relies on open
\n platforms that enable the flexible and scalable training of robots by
\n combining traditional (deterministic) programming with modern AI
\n models (Vision-Language-Action (VLA) models), integrating visual
\n information, language comprehension and robot actions. The goal is a
\n modular robotics ecosystem in which diverse systems work together.
\n This creates a technical basis for new functionality and a wide
\n variety of industrial applications.<\/p>\n
This requires reliable data. At Plant Landshut, the project team
\n captures data from real production environments and test setups, and
\n integrates it into robot simulations, in which movement patterns and
\n motion planning are modelled virtually. This enables processes to be
\n tested in advance and learning processes to be accelerated. New
\n approaches are initially trialled outside of ongoing production,
\n implemented in pilot projects and then scaled up in stages.<\/p>\n
In parallel, humanoid robotic systems acquire new skill sets through
\n demonstration-based learning. In this process, movement patterns and
\n work sequences are first demonstrated by the project team. The data
\n generated in this way is collected by camera systems, motion capture
\n suits and data gloves. It is then converted into generalisable
\n behavioural models \u2013 known as policies \u2013 that can be applied to
\n different tasks and use cases.<\/p>\n
\u201cFor us, it is crucial to develop the technology in very close
\n alignment with real-world requirements. We are not just testing what
\n is technically possible, but also where humanoid robotics can truly
\n deliver reliable benefits in component production. This gradually
\n creates a clear picture of which applications are suitable for
\n industrial use,\u201d says\u00a0Christoph Jagoda, the Physical AI
\n project manager at BMW Group Plant Landshut.\u00a0<\/p>\n
\u00a0<\/p>\n
\n Potential uses in component production
On this basis, Plant Landshut is working on applications for
\n humanoid robotics in component production. The focus is on tasks
\n requiring a high degree of flexibility, fine-motor skills and a good
\n understanding of objects and working environments. This includes
\n recognising and interpreting environments, determining position and
\n status, planning efficient movements, and precisely gripping and
\n moving components.<\/p>\n
To refine the basic technology, the BMW Group is working closely at
\n its Landshut site with partners from industry and academia. This
\n includes, in particular, direct cooperation with Athenyx Robotics, a
\n startup founded specifically for this field of technology that
\n originated at the Laboratory for Machine Tools and Production
\n Engineering (WZL) at RWTH Aachen University and is located in close
\n proximity to BMW Group Plant Landshut.<\/p>\n
The tech company is developing AI-based software for intelligent
\n robotic systems in conjunction with BMW Group specialists. The primary
\n focus is on creating a so-called \u201cintelligence stack\u201d that integrates
\n perception, learning, simulation and decision-making. The aim is to
\n enable humanoid robots to perform complex tasks in industrial
\n environments independently. This requires the systems to be able to
\n perceive their environment, evaluate situations and derive appropriate
\n actions accordingly. The platform-based approach means that acquired
\n skills can be transferred across different robotic systems and use
\n cases in the future.<\/p>\n
In addition, Plant Landshut is collaborating with specialists the
\n University of Applied Sciences Landshut \u2013 for example, on data
\n generation, simulation and the development and testing of specific use cases.<\/p>\n","protected":false},"excerpt":{"rendered":"Landshut. The BMW Group is expanding its expertise in the field of physical AI, with BMW Group Plant…\n","protected":false},"author":2,"featured_media":58351,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20955],"tags":[6213,45636,7561,21118,25301,43],"class_list":["post-58350","post","type-post","status-publish","format-standard","has-post-thumbnail","category-bmw","tag-bmw","tag-landshut","tag-production","tag-recycling","tag-sites","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/germany\/wp-json\/wp\/v2\/posts\/58350","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/germany\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/germany\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/germany\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/germany\/wp-json\/wp\/v2\/comments?post=58350"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/germany\/wp-json\/wp\/v2\/posts\/58350\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/germany\/wp-json\/wp\/v2\/media\/58351"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/germany\/wp-json\/wp\/v2\/media?parent=58350"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/germany\/wp-json\/wp\/v2\/categories?post=58350"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/germany\/wp-json\/wp\/v2\/tags?post=58350"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}