Isaac Gym offers a high performance learning platform to train policies for wide variety of robotics tasks directly on GPU. Both physics simulation and the neural network policy training reside on GPU and communicate by directly passing data from physics buffers to PyTorch tensors without ever going through any CPU bottlenecks. This leads to blazing fast training times for complex robotics tasks on a single GPU with 2-3 orders of magnitude improvements compared to conventional RL training that uses a CPU based simulator and GPU for neural networks.
The Naval Postgraduate Schools (NPS) Consortium for Robotics and Unmanned Systems Education and Research (CRUSER), chartered by the Secretary of the Navy, shapes generations of naval officers through education, research, concept generation and experimentation in maritime applications of robotics, automation and unmanned systems” and “provides a DoD-wide community of interest (COI) to exchange research and experimentation results.”
The Chinese Army is preparing to deploy small, new, tracked war-robots armed with machine guns, night vision, missile loaders and camera sensors to conduct attacks while leaving manned systems at safer stand-off distances.
The US Army Futures Command is issuing a solicitation request to industry to collect information on emerging robotics and sensor technologies for small tactical units under the incipient Smart Targeting Environment for Lower Level Assets (STELLA) programme.
Russian company Uralvagonzavod (UVZ) is developing two unmanned variants of the T-72B3 main battle tank (MBT), the Ministry of Defence (MoD) announced on its website on 12 August.
The US Marine Corps (USMC) is looking toward a future where the battlefield is littered with combatant, human-shaped robots and is seeking industry’s help to acquire robotic targets for training.
Intelligent Control and Automation is a scholarly open access, peer-reviewed, quarterly and fully refereed journal focusing on theories, methods and applications in intelligent control and automation. The goal of this journal is to provide a platform for scientists and academicians all over the world to promote, share and discuss various new issues and developments in different areas of intelligent control and automation.
Ein auf zwei Kugellagern rollender, zierlicher Mini-Roboter variiert die Geschwindigkeit seines rechten Rades je nachdem, ob der Fotowiderstand am Bug einen dunklen oder hellen Untergrund meldet. So kann die minimalistische Konstruktion Kanten und Linien verfolgen.
TED Talks As a grad student, Cynthia Breazeal wondered why we were using robots on Mars, but not in our living rooms. The key, she realized: training robots to interact with people. Now she dreams up and builds robots that teach, learn -- and play. Watch for amazing demo footage of a new interactive game for kids.
Computer Software and Intellectual Property Law from the Office of Laboratory Counsel, Patent Department, Lawrence Berkeley National Laboratory. "This web site was written specifically for any LBNL employee who writes computer programs at Lawrence Berkele
The BABEL Development System is a framework intended to cope with the Robotic Software Integration Problem (also known as RSIP) from the perspective of enabling heterogeneity (that is, very different programs from different researchers that need to be int
D. Beßler, M. Pomarlan, and M. Beetz. Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, page 1684–1692. Richland, SC, International Foundation for Autonomous Agents and Multiagent Systems, (2018)