# Multitask Learning for Scalable and Dense Multilayer Bayesian Map Inference

arXiv: https://arxiv.org/abs/2106.14986 · HTML: https://mlsanity.com/paper/2106.14986/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2021.

## Built on by (most cited first, 7 of 7)

- [MEM: Multi-Modal Elevation Mapping for Robotics and Learning](https://mlsanity.com/paper/2309.16818/) (2023)
- [Energy-based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement Learning](https://mlsanity.com/paper/2207.03034/) (2022)
- [Dynamic Semantic Occupancy Mapping using 3D Scene Flow and Closed-Form Bayesian Inference](https://mlsanity.com/paper/2108.03180/) (2021)
- [TOP-Nav: Legged Navigation Integrating Terrain, Obstacle and Proprioception Estimation](https://mlsanity.com/paper/2404.15256/) (2024)
- [LatentBKI: Open-Dictionary Continuous Mapping in Visual-Language Latent Spaces with Quantifiable Uncertainty](https://mlsanity.com/paper/2410.11783/) (2024)
- [Real-Time Metric-Semantic Mapping for Autonomous Navigation in Outdoor Environments](https://mlsanity.com/paper/2412.00291/) (2024)
- [CARE: Confidence-rich Autonomous Robot Exploration using Bayesian Kernel Inference and Optimization](https://mlsanity.com/paper/2309.05200/) (2023)

## Abstract (arXiv)

This article presents a novel and flexible multitask multilayer Bayesian mapping framework with readily extendable attribute layers. The proposed framework goes beyond modern metric-semantic maps to provide even richer environmental information for robots in a single mapping formalism while exploiting intralayer and interlayer correlations. It removes the need for a robot to access and process information from many separate maps when performing a complex task, advancing the way robots interact with their environments. To this end, we design a multitask deep neural network with attention mechanisms as our front-end to provide heterogeneous observations for multiple map layers simultaneously. Our back-end runs a scalable closed-form Bayesian inference with only logarithmic time complexity. We apply the framework to build a dense robotic map including metric-semantic occupancy and traversability layers. Traversability ground truth labels are automatically generated from exteroceptive sensory data in a self-supervised manner. We present extensive experimental results on publicly available datasets and data collected by a 3D bipedal robot platform and show reliable mapping performance in different environments. Finally, we also discuss how the current framework can be extended to incorporate more information such as friction, signal strength, temperature, and physical quantity concentration using Gaussian map layers. The software for reproducing the presented results or running on customized data is made publicly available.