Autonomous mobile robot navigation in uneven and unstructured indoor environments

Wang, Chaoqun; Meng, Lili; She, Sizhen; Mitchell, Ian M.; Li, Teng; Tung, Frederick; Wan, Weiwei; Meng, Max Q.-H.; Silva, Clarence W. de

doi:10.1109/iros.2017.8202145

Cited by 86 publications

(30 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For future work, implementing on a parallel computation architecture will make the current work more efficient. Moreover, it will be interesting to integrate our camera relocalization to an autonomous robot navigation system [39] .…”

Section: Discussionmentioning

confidence: 99%

Backtracking regression forests for accurate camera relocalization

Meng¹,

Chen²,

Tung³

et al. 2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

Camera relocalization plays a vital role in many robotics and computer vision tasks, such as global localization, recovery from tracking failure, and loop closure detection. Recent random forests based methods directly predict 3D world locations for 2D image locations to guide the camera pose optimization. During training, each tree greedily splits the samples to minimize the spatial variance. However, these greedy splits often produce uneven sub-trees in training or incorrect 2D-3D correspondences in testing. To address these problems, we propose a sample-balanced objective to encourage equal numbers of samples in the left and right sub-trees, and a novel backtracking scheme to remedy the incorrect 2D-3D correspondence predictions. Furthermore, we extend the regression forests based methods to use local features in both training and testing stages for outdoor RGB-only applications. Experimental results on publicly available indoor and outdoor datasets demonstrate the efficacy of our approach, which shows superior or on-par accuracy with several state-of-theart methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Backtracking regression forests for accurate camera relocalization

Meng¹,

Chen²,

Tung³

et al. 2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Wheeled robots can thus avoid excessive wheel slip and sinking. This will save energy, improve safety and reduce odometer error for wheeled robots [6,7]. Overly strong vibrations will seriously affect the accuracy of the robot's camera, lidar, IMU and other sensors [8].…”

Section: Introductionmentioning

confidence: 99%

A Vision-Based Two-Stage Framework for Inferring Physical Properties of the Terrain

et al. 2020

View full text Add to dashboard Cite

The friction and stiffness properties of the terrain are very important pieces of information for mobile robots in motion control, dynamics parameter adjustment, trajectory planning, etc. Inferring the friction and stiffness properties in advance can improve the safety, adaptability and reliability, and reduce the energy consumption of the robot. This paper proposes a vision-based two-stage framework for pre-estimating physical properties of the terrain. We established a field terrain image dataset with weak annotations. A semantic segmentation network that can segment terrains at the pixel level was designed. Given that the same terrain also has different physical properties, we designed two kinds of image features, and we use a decision-making model to realize the mapping from terrain to physical properties. We trained and tested the network comprehensively, and experimented with the complete framework for estimating physical properties. The experimental results show that our framework has good performance.

show abstract

“…For future work, it will be promising to improve our current method to be more robust to dynamic environments such as using weighted edge points [47]. Moreover, implementing our current method on a GPU will be more efficient [41] and it will also be interesting to integrate our method for a robot autonomous navigation system [48].…”

Section: Discussionmentioning

confidence: 99%

Exploiting Points and Lines in Regression Forests for RGB-D Camera Relocalization

Meng

Tung

Little

et al. 2018

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

Camera relocalization plays a vital role in many robotics and computer vision applications, such as self-driving cars and virtual reality. Recent random forests based methods exploit randomly sampled pixel comparison features to predict 3D world locations for 2D image locations to guide the camera pose optimization. However, these point features are only sampled randomly in images, without considering geometric information such as lines, leading to large errors with the existence of poorly textured areas or in motion blur. Line segments are more robust in these environments. In this work, we propose to jointly exploit points and lines within the framework of uncertainty driven regression forests. The proposed approach is thoroughly evaluated on three publicly available datasets against several strong state-of-the-art baselines in terms of several different error metrics. Experimental results prove the efficacy of our method, showing superior or on-par state-ofthe-art performance.

show abstract

Autonomous mobile robot navigation in uneven and unstructured indoor environments

Cited by 86 publications

References 37 publications

Backtracking regression forests for accurate camera relocalization

Backtracking regression forests for accurate camera relocalization

A Vision-Based Two-Stage Framework for Inferring Physical Properties of the Terrain

Exploiting Points and Lines in Regression Forests for RGB-D Camera Relocalization

Contact Info

Product

Resources

About