Periodic Reporting for period 1 - iNavigate (Brain-inspired technologies for intelligent navigation and mobility)
Période du rapport: 2019-12-01 au 2023-05-31
Intelligent machines like robots and self-driving cars can free up cognitive resources, increase productivity, and improve healthcare. However, to perform well they require specific instructions that are context- and task-bound. In fact, autonomous machines may err in novel, surprising environments, with sometimes fatal consequences. Humans and animals, by contrast, navigate ever-changing environments successfully, unless they are suffering from ailments like aging-related memory decline. Therefore, the goal of iNAVIGATE is to infer the principles of surprise-based navigation from behavioral and neural data of fish, rodents, and humans, and to implement and test these principles in mobile robots and bionic devices, thereby providing novel technological solutions for autonomous robotic mobility. To achieve this goal, academic and non-academic partners consisting of behavioral scientists, neuroscientists, computer scientists, and roboticists, residing in the EU/AC and the USA, conduct joint research on intelligent navigation. Professional development, new skill acquisition, and career advancement are achieved through international and inter-sectoral mobility, research and innovation, and knowledge transfer during summer schools, workshops, and networking events.
Towards Objective O1.1 (Identify how organisms across different evolutionary scales adapt to sensory uncertainty during navigation), hardware and software were developed for the high throughput study of navigation in different species, and behavioral data were also collected.
Towards Objective O2.1 (Provide a mechanistic insight into the neural network computations that drive navigation), work carried out during three secondments (BU-3Dneuro, HSRW-muZIEum, and RU-BMW) focused on creating new neural recording capabilities in freely moving rodents and humans.
Towards Objectives O3.1 (Approximate the network computations that drive animal navigation) and O3.2 (Define the influence of individual nodes in the network to the network computations), beneficiary AU has proposed a framework in which fish decisions are modelled at the algorithmic level.
Towards Objective O4.1 (Implement brain-inspired control algorithms in robotic instruments), in a pilot study that was part of a secondment from HSRW to the muZIEum, a first rat-based navigation algorithm was implemented on a TurtleBot.
Towards Objective O2.1 (Provide a mechanistic insight into the neural network computations that drive navigation), work carried out during three secondments (BU-3Dneuro, HSRW-muZIEum, and RU-BMW) focused on creating new neural recording capabilities in freely moving rodents and humans.
Towards Objectives O3.1 (Approximate the network computations that drive animal navigation) and O3.2 (Define the influence of individual nodes in the network to the network computations), beneficiary AU has proposed a framework in which fish decisions are modelled at the algorithmic level.
Towards Objective O4.1 (Implement brain-inspired control algorithms in robotic instruments), in a pilot study that was part of a secondment from HSRW to the muZIEum, a first rat-based navigation algorithm was implemented on a TurtleBot.
We expect that iNavigate will contribute to skillset development, including core research skills acquired during secondments in individual projects, multidisciplinary advanced/additional research skills provided in network-wide training events (e.g. trainings in neural recording and neuromodulation, computer programming, and robotics), and know-how of research ethics, intellectual property, commercialization, entrepreneurship and business plan development, as well as social impact awareness, public speaking and scientific/technical writing.