Robot Localization in Floor Plans Using a Room Layout Edge Extraction Network

Boniardi, Federico; Valada, Abhinav; Mohan, Renjith; Caselitz, Tim; Burgard, Wolfram

doi:10.1109/iros40897.2019.8967847

Cited by 38 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…to the location of a sound-emitting source using audio and visual signals [9,21], semantic audio-visual navigation [8] with coherent room and sound semantics, active perception tasks such as active audio-visual source separation [30] and audiovisual dereverberation [11], curiosity-based exploration via audio-visual association [46] as well as tasks explicitly focusing on the geometric information contained in audio such as audio-visual floor plan reconstruction [5,35].…”

Section: Introductionmentioning

confidence: 99%

Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds

Younes¹,

Honerkamp²,

Welschehold³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Audio-visual navigation combines sight and hearing to navigate to a sound-emitting source in an unmapped environment. While recent approaches have demonstrated the benefits of audio input to detect and find the goal, they focus on clean and static sound sources and struggle to generalize to unheard sounds. In this work, we propose the novel dynamic audio-visual navigation benchmark which requires to catch a moving sound source in an environment with noisy and distracting sounds. We introduce a reinforcement learning approach that learns a robust navigation policy for these complex settings. To achieve this, we propose an architecture that fuses audio-visual information in the spatial feature space to learn correlations of geometric information inherent in both local maps and audio signals. We demonstrate that our approach consistently outperforms the current state-of-the-art by a large margin across all tasks of moving sounds, unheard sounds, and noisy environments, on two challenging 3D scanned real-world environments, namely Matterport3D and Replica. The benchmark is available at http://dav-nav.cs.uni-freiburg.de.

show abstract

Section: Introductionmentioning

confidence: 99%

Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds

Younes¹,

Honerkamp²,

Welschehold³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Autonomous vehicles (AVs) rely on accurate semantic understanding of their surroundings for reliable and safe operation. Scene segmentation is extensively used in various applications such as dynamic object removal [1] and localization [2] as it enables distinguishing points that belong to different objects and classes. It can be classified into three tasks, namely, semantic segmentation which predicts a class label for each point, instance segmentation which assigns a unique ID to points belonging to each object, and panoptic segmentation which combines both semantic and instance segmentation to yield a holistic output containing both stuff and thing classes.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Domain Adaptation for LiDAR Panoptic Segmentation

Bešić,

Gosala,

Cattaneo

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Scene understanding is a pivotal task for autonomous vehicles to safely navigate in the environment. Recent advances in deep learning enable accurate semantic reconstruction of the surroundings from LiDAR data. However, these models encounter a large domain gap while deploying them on vehicles equipped with different LiDAR setups which drastically decreases their performance. Fine-tuning the model for every new setup is infeasible due to the expensive and cumbersome process of recording and manually labeling new data. Unsupervised Domain Adaptation (UDA) techniques are thus essential to fill this domain gap and retain the performance of models on new sensor setups without the need for additional data labeling. In this paper, we propose AdaptLPS, a novel UDA approach for LiDAR panoptic segmentation that leverages task-specific knowledge and accounts for variation in the number of scan lines, mounting position, intensity distribution, and environmental conditions. We tackle the UDA task by employing two complementary domain adaptation strategies, data-based and model-based. While databased adaptations reduce the domain gap by processing the raw LiDAR scans to resemble the scans in the target domain, modelbased techniques guide the network in extracting features that are representative for both domains. Extensive evaluations on three pairs of real-world autonomous driving datasets demonstrate that AdaptLPS outperforms existing UDA approaches by up to 6.41 pp in terms of the PQ score.

show abstract

“…The underlying 3D structures of an indoor scene, such as a floor plan of a building or layouts of multiple rooms, play a crucial role for a holistic robot perception as detailed in [1]- [6]. Despite their simplicity, these high-level geometry abstractions can complement challenging tasks such as obstacle avoidance [3], robot localization [4], path planning [5], and scene understanding [6]; hence, a handy and direct estimation of a floor plan geometry is our primary motivation.…”

Section: Introductionmentioning

confidence: 99%

360-DFPE: Leveraging Monocular 360-Layouts for Direct Floor Plan Estimation

Solarte¹,

Liu²,

Wu³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present 360-DFPE, a sequential floor plan estimation method that directly takes 360-images as input without relying on active sensors or 3D information. Our approach leverages a loosely coupled integration between a monocular visual SLAM solution and a monocular 360-room layout approach, which estimate camera poses and layout geometries, respectively.Since our task is to sequentially capture the floor plan using monocular images, the entire scene structure, room instances, and room shapes are unknown. To tackle these challenges, we first handle the scale difference between visual odometry and layout geometry via formulating an entropy minimization process, which enables us to directly align 360layouts without knowing the entire scene in advance. Second, to sequentially identify individual rooms, we propose a novel room identification algorithm that tracks every room along the camera exploration using geometry information. Lastly, to estimate the final shape of the room, we propose a shortest path algorithm with an iterative coarse-to-fine strategy, which improves prior formulations with higher accuracy and faster run-time. Moreover, we collect a new floor plan dataset with challenging large-scale scenes, providing both point clouds and sequential 360-image information. Experimental results show that our monocular solution achieves favorable performance against the current state-of-the-art algorithms that rely on active sensors and require the entire scene reconstruction data in advance. We will release our code and dataset.

show abstract

Robot Localization in Floor Plans Using a Room Layout Edge Extraction Network

Cited by 38 publications

References 22 publications

Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds

Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds

Unsupervised Domain Adaptation for LiDAR Panoptic Segmentation

360-DFPE: Leveraging Monocular 360-Layouts for Direct Floor Plan Estimation

Contact Info

Product

Resources

About