Abstract
Insect neural systems are a promising source of inspiration for new navigation algorithms, especially on low size, weight, and power platforms. There have been unprecedented recent neuroscience breakthroughs with Drosophila in behavioral and neural imaging experiments as well as the mapping of detailed connectivity of neural structures. General mechanisms for learning orientation in the central complex (CX) of Drosophila have been investigated previously; however, it is unclear how these underlying mechanisms extend to cases where there is translation through an environment (beyond only rotation), which is critical for navigation in robotic systems. Here, we develop a CX neural connectivity-constrained model that performs sensor fusion, as well as unsupervised learning of visual features for path integration; we demonstrate the viability of this circuit for use in robotic systems in simulated and physical environments. Furthermore, we propose a theoretical understanding of how distributed online unsupervised network weight modification can be leveraged for learning in a trajectory through an environment by minimizing orientation estimation error. Overall, our results may enable a new class of CX-derived low power robotic navigation algorithms and lead to testable predictions to inform future neuroscience experiments.
Highlights
Insect neural systems are a promising source of inspiration for new navigation algorithms, especially on low size, weight, and power platforms
Our model transforms angular velocity and visual features into a fused representation of orientation utilizing a total of 141 neurons distributed across five populations of neurons as specified in Fig. 1A, which are constrained by connectivity patterns of neuron types observed in Drosophila across glomeruli, and with plastic synaptic connections that enable the learning of visual landmarks
The five types of modeled neurons all synapse in either the protocerebral bridge (PB) or ellipsoid body (EB) regions of the CX and include: (1) Ring neurons which are receptive to visual inputs, (2) PB-EB-Noduli (P-EN) neurons which receive angular velocity inputs, (3) EB-PB-Gall neurons (E-PG) neurons, (4) PB-EB-Gall (P-EG) neurons, and (5) intrinsic neurons of the PB (PIntr), referred to as Δ7 neurons
Summary
Insect neural systems are a promising source of inspiration for new navigation algorithms, especially on low size, weight, and power platforms. Many visual odometry approaches for state estimation exist[7], including high performing Visual-Inertial Odometry (VIO) systems for state estimation on rapidly moving p latforms[6]. These approaches require simplifying linearization assumptions[8], which can be addressed with more computationally intensive approaches such as particle filtering[9]. Promising approaches in deep learning for unsupervised training of visual odometry approaches include the intermediate calculation of depth from images, which can be refined in tandem with pose estimation by offline network optimization on a collected dataset[21]. In general training of the neural networks utilized in visual navigation are not performed during robotic system deployment due to computational requirements for training and the number of required training samples
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
