Exploiting semantic information in a spiking neural SLAM system
To navigate in new environments, an animal must be able to keep track of its position while simultaneously creating and updating an internal map of features in the environment, a problem formulated as simultaneous localization and mapping (SLAM) in the field of robotics. This requires integrating in...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2023.1190515/full |
| _version_ | 1797786854446071808 |
|---|---|
| author | Nicole Sandra-Yaffa Dumont P. Michael Furlong Jeff Orchard Chris Eliasmith |
| author_facet | Nicole Sandra-Yaffa Dumont P. Michael Furlong Jeff Orchard Chris Eliasmith |
| author_sort | Nicole Sandra-Yaffa Dumont |
| collection | DOAJ |
| description | To navigate in new environments, an animal must be able to keep track of its position while simultaneously creating and updating an internal map of features in the environment, a problem formulated as simultaneous localization and mapping (SLAM) in the field of robotics. This requires integrating information from different domains, including self-motion cues, sensory, and semantic information. Several specialized neuron classes have been identified in the mammalian brain as being involved in solving SLAM. While biology has inspired a whole class of SLAM algorithms, the use of semantic information has not been explored in such work. We present a novel, biologically plausible SLAM model called SSP-SLAM—a spiking neural network designed using tools for large scale cognitive modeling. Our model uses a vector representation of continuous spatial maps, which can be encoded via spiking neural activity and bound with other features (continuous and discrete) to create compressed structures containing semantic information from multiple domains (e.g., spatial, temporal, visual, conceptual). We demonstrate that the dynamics of these representations can be implemented with a hybrid oscillatory-interference and continuous attractor network of head direction cells. The estimated self-position from this network is used to learn an associative memory between semantically encoded landmarks and their positions, i.e., an environment map, which is used for loop closure. Our experiments demonstrate that environment maps can be learned accurately and their use greatly improves self-position estimation. Furthermore, grid cells, place cells, and object vector cells are observed by this model. We also run our path integrator network on the NengoLoihi neuromorphic emulator to demonstrate feasibility for a full neuromorphic implementation for energy efficient SLAM. |
| first_indexed | 2024-03-13T01:14:44Z |
| format | Article |
| id | doaj.art-922f278359494b6bb5a83ceeca356869 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-03-13T01:14:44Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-922f278359494b6bb5a83ceeca3568692023-07-05T12:38:33ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2023-07-011710.3389/fnins.2023.11905151190515Exploiting semantic information in a spiking neural SLAM systemNicole Sandra-Yaffa DumontP. Michael FurlongJeff OrchardChris EliasmithTo navigate in new environments, an animal must be able to keep track of its position while simultaneously creating and updating an internal map of features in the environment, a problem formulated as simultaneous localization and mapping (SLAM) in the field of robotics. This requires integrating information from different domains, including self-motion cues, sensory, and semantic information. Several specialized neuron classes have been identified in the mammalian brain as being involved in solving SLAM. While biology has inspired a whole class of SLAM algorithms, the use of semantic information has not been explored in such work. We present a novel, biologically plausible SLAM model called SSP-SLAM—a spiking neural network designed using tools for large scale cognitive modeling. Our model uses a vector representation of continuous spatial maps, which can be encoded via spiking neural activity and bound with other features (continuous and discrete) to create compressed structures containing semantic information from multiple domains (e.g., spatial, temporal, visual, conceptual). We demonstrate that the dynamics of these representations can be implemented with a hybrid oscillatory-interference and continuous attractor network of head direction cells. The estimated self-position from this network is used to learn an associative memory between semantically encoded landmarks and their positions, i.e., an environment map, which is used for loop closure. Our experiments demonstrate that environment maps can be learned accurately and their use greatly improves self-position estimation. Furthermore, grid cells, place cells, and object vector cells are observed by this model. We also run our path integrator network on the NengoLoihi neuromorphic emulator to demonstrate feasibility for a full neuromorphic implementation for energy efficient SLAM.https://www.frontiersin.org/articles/10.3389/fnins.2023.1190515/fullsimultaneous localization and mappingsemantic SLAMpath integrationspiking neural networksneuromorphichyperdimensional computing |
| spellingShingle | Nicole Sandra-Yaffa Dumont P. Michael Furlong Jeff Orchard Chris Eliasmith Exploiting semantic information in a spiking neural SLAM system Frontiers in Neuroscience simultaneous localization and mapping semantic SLAM path integration spiking neural networks neuromorphic hyperdimensional computing |
| title | Exploiting semantic information in a spiking neural SLAM system |
| title_full | Exploiting semantic information in a spiking neural SLAM system |
| title_fullStr | Exploiting semantic information in a spiking neural SLAM system |
| title_full_unstemmed | Exploiting semantic information in a spiking neural SLAM system |
| title_short | Exploiting semantic information in a spiking neural SLAM system |
| title_sort | exploiting semantic information in a spiking neural slam system |
| topic | simultaneous localization and mapping semantic SLAM path integration spiking neural networks neuromorphic hyperdimensional computing |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2023.1190515/full |
| work_keys_str_mv | AT nicolesandrayaffadumont exploitingsemanticinformationinaspikingneuralslamsystem AT pmichaelfurlong exploitingsemanticinformationinaspikingneuralslamsystem AT jefforchard exploitingsemanticinformationinaspikingneuralslamsystem AT chriseliasmith exploitingsemanticinformationinaspikingneuralslamsystem |