Recurrent-OctoMap: Learning State-based Map Refinement for Long-Term Semantic Mapping with 3D-Lidar Data
This addresses the challenge of improving semantic mapping over time for robotics or autonomous systems in dynamic environments, representing an incremental advance over existing methods.
The paper tackles the problem of 3D semantic map refinement from long-term 3D Lidar data by proposing Recurrent-OctoMap, a learning-based approach that models map cells as recurrent neural networks to fuse semantic features, and it outperforms the conventional Bayesian update method on the ETH dataset.
This paper presents a novel semantic mapping approach, Recurrent-OctoMap, learned from long-term 3D Lidar data. Most existing semantic mapping approaches focus on improving semantic understanding of single frames, rather than 3D refinement of semantic maps (i.e. fusing semantic observations). The most widely-used approach for 3D semantic map refinement is a Bayesian update, which fuses the consecutive predictive probabilities following a Markov-Chain model. Instead, we propose a learning approach to fuse the semantic features, rather than simply fusing predictions from a classifier. In our approach, we represent and maintain our 3D map as an OctoMap, and model each cell as a recurrent neural network (RNN), to obtain a Recurrent-OctoMap. In this case, the semantic mapping process can be formulated as a sequence-to-sequence encoding-decoding problem. Moreover, in order to extend the duration of observations in our Recurrent-OctoMap, we developed a robust 3D localization and mapping system for successively mapping a dynamic environment using more than two weeks of data, and the system can be trained and deployed with arbitrary memory length. We validate our approach on the ETH long-term 3D Lidar dataset [1]. The experimental results show that our proposed approach outperforms the conventional "Bayesian update" approach.