Aditya Dhawale

Carnegie Mellon University, Corvallis Environmental Center

Papers

Total Citations

H-Index

About

Aditya Dhawale’s research lies at the intersection of robotics, autonomous navigation, and probabilistic mapping, with a focus on enabling real-time, computationally efficient perception for resource-constrained platforms. His major contributions center on developing novel Gaussian-based representations for dense and reactive mapping. In his highly cited work on *Reactive Collision Avoidance Using Real-Time Local Gaussian Mixture Model Maps* (23 citations), Dhawale introduced a probabilistic approach that replaces discrete, memory-intensive maps with a continuous Gaussian Mixture Model, allowing robots to perform online collision checking in unknown, cluttered environments with drastically reduced computational overhead. Building on this, his *Efficient Parametric Multi-Fidelity Surface Mapping* (18 citations) addressed the critical challenge of deploying dense 3D mapping on Size, Weight, and Power (SWaP) constrained systems. By leveraging parametric Gaussian distributions, his method achieves accurate, multi-fidelity surface reconstruction without the prohibitive memory and compute demands of state-of-the-art dense mapping. Dhawale’s work is notable for bridging the gap between theoretical probabilistic robotics and practical deployment on embedded systems, directly impacting the feasibility of autonomous navigation for drones, rovers, and other lightweight robots. His contributions are essential reading for researchers working on real-time perception and collision avoidance in field robotics.