A Multi-Sensor Next-Best-View Framework for Geometric Model-Based Robotics Applications

Cui, Jinda; Wen, John T.; Trinkle, Jeff

doi:10.1109/icra.2019.8794423

Cited by 6 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparing information gain formulations in the multi-sensor case is a direction for future work. The demands for NBV planning vary depending on the application [8], [11], [12], and studying the quality of the reconstructions with respect to the parameters of the algorithm can help fit our proposed method to specific applications.…”

Section: Discussionmentioning

confidence: 99%

“…The algorithm proposed in [3] is applied to decentralize the planning task so that each robot can plan its views without needing to constantly communicate with the other robots. Cui et al [12] select if a robot should apply a laser range finder or depth camera next. Candidate sensing actions are scored by a weighted sum of the number of unknown voxels, occupied voxels, and voxels neighbouring a free voxel.…”

Section: A Next-best-view Planningmentioning

confidence: 99%

“…We do not focus on ROIs, but strive for a complete reconstruction. Different to [12], we choose the views of multiple sensors simultaneously. By applying submodular maximization, we provide a performance guarantee for our planning algorithm.…”

Section: A Next-best-view Planningmentioning

confidence: 99%

“…1) with reliable communication. Cui et al [12] consider a single robot equipped with many sensors, one of which is chosen to be active at any time. In contrast, we consider joint planning where all sensors are operated simultaneously and the combination of views that is most useful is selected.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization

Lauri

Pajarinen

Peters

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

3D scene models are useful in robotics for tasks such as path planning, object manipulation, and structural inspection. We consider the problem of creating a 3D model using depth images captured by a team of multiple robots. Each robot selects a viewpoint and captures a depth image from it, and the images are fused to update the scene model. The process is repeated until a scene model of desired quality is obtained. Next-best-view planning uses the current scene model to select the next viewpoints. The objective is to select viewpoints so that the images captured using them improve the quality of the scene model the most. In this paper, we address nextbest-view planning for multiple depth cameras. We propose a utility function that scores sets of viewpoints and avoids overlap between multiple sensors. We show that multi-sensor next-best-view planning with this utility function is an instance of submodular maximization under a matroid constraint. This allows the planning problem to be solved by a polynomial-time greedy algorithm that yields a solution within a constant factor from the optimal. We evaluate the performance of our planning algorithm in simulated experiments with up to 8 sensors, and in real-world experiments using two robot arms equipped with depth cameras.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: A Next-best-view Planningmentioning

confidence: 99%

Section: A Next-best-view Planningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization

Lauri

Pajarinen

Peters

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Triangle mesh representation is a common form of 3D model [27,28]. Some view planning works [8,29] use a triangle mesh to represent the intermediate state of the environment. A triangle mesh can well capture fine details on the surfaces of scanned objects.…”

Section: Triangle Meshesmentioning

confidence: 99%

View planning in robot active vision: A survey of systems, algorithms, and applications

et al. 2020

View full text Add to dashboard Cite

Rapid development of artificial intelligence motivates researchers to expand the capabilities of intelligent and autonomous robots. In many robotic applications, robots are required to make planning decisions based on perceptual information to achieve diverse goals in an efficient and effective way. The planning problem has been investigated in active robot vision, in which a robot analyzes its environment and its own state in order to move sensors to obtain more useful information under certain constraints. View planning, which aims to find the best view sequence for a sensor, is one of the most challenging issues in active robot vision. The quality and efficiency of view planning are critical for many robot systems and are influenced by the nature of their tasks, hardware conditions, scanning states, and planning strategies. In this paper, we first summarize some basic concepts of active robot vision, and then review representative work on systems, algorithms and applications from four perspectives: object reconstruction, scene reconstruction, object recognition, and pose estimation. Finally, some potential directions are outlined for future work.

show abstract

A one-shot next best view system for active object recognition

2021

View full text Add to dashboard Cite

A Multi-Sensor Next-Best-View Framework for Geometric Model-Based Robotics Applications

Cited by 6 publications

References 10 publications

Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization

Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization

View planning in robot active vision: A survey of systems, algorithms, and applications

A one-shot next best view system for active object recognition

Contact Info

Product

Resources

About