5 papers
HyperSpace: A Generalized Framework for Spatial Encoding in Hyperdimensional Representations
Shay Snyder, Andrew Capodieci, David Gorsich +1
Vector Symbolic Architectures (VSAs) provide a well-defined algebraic framework for compositional representations in hyperdimensional spaces. We introduce HyperSpace, an open-sourc…
SRMU: Relevance-Gated Updates for Streaming Hyperdimensional Memories
Shay Snyder, Andrew Capodieci, David Gorsich +1
Sequential associative memories (SAMs) are difficult to build and maintain in real-world streaming environments, where observations arrive incrementally over time, have imbalanced…
Brain Inspired Probabilistic Occupancy Grid Mapping with Vector Symbolic Architectures
Shay Snyder, Andrew Capodieci, David Gorsich +1
Real-time robotic systems require advanced perception, computation, and action capability. However, the main bottleneck in current autonomous systems is the trade-off between compu…
Generalizable Reinforcement Learning with Biologically Inspired Hyperdimensional Occupancy Grid Maps for Exploration and Goal-Directed Path Planning
Shay Snyder, Ryan Shea, Andrew Capodieci +2
Real-time autonomous systems utilize multi-layer computational frameworks to perform critical tasks such as perception, goal finding, and path planning. Traditional methods impleme…
ConvBKI: Real-Time Probabilistic Semantic Mapping Network with Quantifiable Uncertainty
Joey Wilson, Yuewei Fu, Joshua Friesen +5
In this paper, we develop a modular neural network for real-time {\color{black}(> 10 Hz)} semantic mapping in uncertain environments, which explicitly updates per-voxel probabilist…