Real-time robotic systems require advanced perception and action capability. However, the main bottleneck in current autonomous systems is the trade-off between computational capability, energy efficiency, and model determinism. World modeling, a key objective of many robotic systems, commonly uses occupancy grid mapping (OGM) as the first step towards building an end-to-end robotic system. OGM discretizes the environment into cells and assigns probability values to attributes such as occupancy. Existing methods fall into two categories: traditional methods and neural methods. Traditional methods leverage dense statistical calculations, while neural methods employ deep learning for probabilistic information processing. We propose a vector symbolic architecture-based OGM system (VSA-OGM) that retains the interpretability and stability of traditional methods with the improved computational efficiency of neural methods. VSA-OGM, validated across multiple datasets, achieves similar accuracy to covariant traditional methods while reducing latency and memory by 45× and 400×, respectively. Compared to invariant traditional methods, VSA-OGM maintains similar accuracy values while reducing latency by 5.5×. Moreover, VSA-OGM achieves 6x latency reductions compared to neural methods while eliminating the need for domain-specific training. This work demonstrates the potential of VSA-OGM as a foundation for efficient OGM in autonomous systems operating under strict computational and latency constraints.
Snyder et al. (2026) studied this question.