ConvBKI: Real-Time Probabilistic Semantic Mapping Network with Quantifiable Uncertainty
This work addresses the need for trustworthy, real-time semantic mapping in robotics, particularly for perceptually challenging environments like off-road driving, though it appears incremental as it hybridizes existing approaches.
The paper tackles real-time semantic mapping in uncertain environments by introducing ConvBKI, a neural network layer that updates probabilistic distributions per voxel, achieving over 10 Hz performance and combining reliability from classical methods with efficiency from neural networks.
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 probabilistic distributions within a neural network layer. Our approach combines the reliability of classical probabilistic algorithms with the performance and efficiency of modern neural networks. Although robotic perception is often divided between modern differentiable methods and classical explicit methods, a union of both is necessary for real-time and trustworthy performance. We introduce a novel Convolutional Bayesian Kernel Inference (ConvBKI) layer which incorporates semantic segmentation predictions online into a 3D map through a depthwise convolution layer by leveraging conjugate priors. We compare ConvBKI against state-of-the-art deep learning approaches and probabilistic algorithms for mapping to evaluate reliability and performance. We also create a Robot Operating System (ROS) package of ConvBKI and test it on real-world perceptually challenging off-road driving data.