Hyperdimensional Computing (HDC) is a brain-inspired, lightweight computing paradigm that has shown great potential for inference on the edge and on emerging hardware technologies, achieving state-of-the-art accuracy on certain classification tasks. HDC classifiers are inherently error resilient and support early termination of inference to approximate classification results. Practitioners have developed heuristic methods to terminate inference early for individual inputs, reducing the computation of inference at the cost of accuracy. These techniques lack statistical guarantees and may unacceptably degrade classification accuracy or terminate inference later than is needed to obtain an accuracy result.

Micro-robots are emerging as powerful tools for search-and-rescue, precision agriculture, and cooperative manipulation, where their small size and low cost offer advantages over larger robots. However, enabling autonomous navigation on these robots remains challenging due to severe hardware constraints, such as limited memory, energy, and computational power. We explore a brain-inspired learning paradigm called Hyperdimensional Computing (HDC) to equip a cheap, lightweight navigation model that runs onboard micro-robots. We present NavHD, which features an adaptive HD encoder that learns spatial representations and incorporates loss-based training for both imitation learning and off-policy reinforcement learning. Our hardware implementation of NavHD uses eight ultrasound sensors and is optimized to run on an ARM Cortex-M4 core, using only 10.2 kB of memory, 900 clock cycles and 1.1 mJ of energy per inference. Through experiments in both simulation and the real world, we demonstrate that NavHD outperforms DNN-based and prior HDC-based RL methods in obstacle avoidance by more than 2x the performance, while achieving 2-26x more superior resource efficiency.

We present HyperCam, an energy-efficient image classification pipeline that enables computer vision tasks onboard low-power IoT camera systems. HyperCam leverages hyper-dimensional computing to perform training and inference efficiently on low-power microcontrollers. We implement a low-power wireless camera platform using off-the-shelf hardware and demonstrate that HyperCam can achieve an accuracy of 93.60%, 84.06%, 92.98%, and 72.79% for MNIST, Fashion-MNIST, Face Detection, and Face Identification tasks, respectively, while significantly outperforming other classifiers in resource efficiency. Specifically, it delivers inference latency of 0.08–0.27s while using 42.91–63.00KB flash memory and 22.25KB RAM at peak. Among other machine learning classifiers such as SVM, xgBoost, MicroNets, MobileNetV3, and MCUNetV3, HyperCam is the only classifier that achieves competitive accuracy while maintaining competitive memory footprint and inference latency that meets the resource requirements of low-power camera systems.

Edge intelligence greatly benefits Internet-of-Things devices by providing insights at the sensor node without transmitting the data to and from the cloud. Although recent work has scaled deep neural networks down to microcontrollers, these solutions remain impractical for devices operating under strict energy budgets—such as battery-powered camera traps in remote forests or micro-robots in disaster zones. My work addresses that gap by exploring a brain-inspired Vector Symbolic Architecture (VSA) over conventional neural networks. I introduce HyperCam for low-power image classification, NavHD for micro-robot navigation, and Omen for dynamic optimization during inference. These methods each optimize VSA's encoding and training algorithms to achieve meaningful speedups and energy savings. Ongoing work seeks to demonstrate these advances as real-world systems, where VSA can extend the lifespan of intelligent systems in remote or energy-constrained environments.