Next-best-scan planning for autonomous 3D modeling

Kriegel, Simon; Rink, Christian; Bodenmüller, Tim; Narr, Alexander; Suppa, Michael; Hirzinger, Gerd

doi:10.1109/iros.2012.6385624

Cited by 46 publications

(32 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…10 The reader can find a thorough review of view planning methods in the following surveys. 1,9,14,20 Some methods go beyond the NBV calculation and determine the robot state that matches the sensor pose Torabi and Gupta, 10 combines inverse kinematics with a probabilistic road map (PRM), Kriegel et al, 2 uses an RRT to get possible paths, and Monica and Aleotti 21 uses optimal motion planning implemented in the MoveIt! ROS stack.…”

Section: Related Workmentioning

confidence: 99%

Tree-based search of the next best view/state for three-dimensional object reconstruction

Vasquez-Gomez

Sucar

Murrieta-Cid

et al. 2018

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Three-dimensional models from real objects have many applications in robotics. To automatically build a three-dimensional model from an object, it is essential to determine where to place the range sensor in order to completely observe the object. However, the view (position and orientation) of the sensor is not sufficient, given that its corresponding robot state needs to be calculated. Additionally, a collision-free trajectory to reach that state is required. In this article, we directly find the state of the robot whose corresponding sensor view observes the object. This method does not require to calculate the inverse kinematics of the robot. Unlike previous approaches, the proposed method guides the search with a tree structure based on a rapidly exploring random tree overcoming previous sampling techniques. In addition, we propose an information metric that improves the reconstruction performance of previous information metrics.

show abstract

Section: Related Workmentioning

confidence: 99%

Tree-based search of the next best view/state for three-dimensional object reconstruction

Vasquez-Gomez

Sucar

Murrieta-Cid

et al. 2018

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…Existing autonomous scanning systems either employ an articulated robotic arm to perform detailed scanning of a single object [Krainin et al 2011;Kriegel et al 2012;Wu et al 2014], or drive a mobile robot equipped with a fixed camera for exploratory scene mapping [Charrow et al 2015]. In contrast to these works, we employ an eye-in-hand setting on a mobile robot to achieve simultaneous exploration and scanning of complex scenes, which requires joint optimization of robot paths and camera trajectories.…”

Section: Related Workmentioning

confidence: 99%

Autonomous reconstruction of unknown indoor scenes guided by time-varying tensor fields

Zheng

Yan

et al. 2017

ACM Trans. Graph.

View full text Add to dashboard Cite

(a) (b) (c) (d) Fig. 1. We introduce an algorithm for the autonomous reconstruction of indoor scenes, based on time-varying tensor fields (a). Given the partially scanned scene, a 2D tensor field is computed on-the-fly over the floor plane, constrained by the partial reconstruction (b). The robot is guided by the field with smooth paths, which are locally formed with field advection (red curve in (a)) and globally planned with the help of the field topology (see the curve networks in (b) and (c), with reconstruction uncertainty color-coded along the curves). The topological structure is well-defined for incomplete scenes (b), suited for guiding exploratory reconstruction of unknown scenes. The output is a full 3D reconstruction (d), at which the topology of the field reflects the scene layout (c).Autonomous reconstruction of unknown scenes by a mobile robot inherently poses the question of balancing between exploration efficacy and reconstruction quality. We present a navigation-by-reconstruction approach to address this question, where moving paths of the robot are planned to account for both global efficiency for fast exploration and local smoothness to obtain high-quality scans. An RGB-D camera, attached to the robot arm, is dictated by the desired reconstruction quality as well as the movement of the robot itself. Our key idea is to harness a time-varying tensor field to guide robot movement, and then solve for 3D camera control under the constraint of the 2D robot moving path. The tensor field is updated in real time, conforming to the progressively reconstructed scene. We show that tensor fields are well suited for guiding autonomous scanning for two reasons: first, they contain sparse and controllable singularities that allow generating a locally smooth robot path, and second, their topological structure can be used for globally efficient path routing within a partially reconstructed scene. We have conducted numerous tests with a mobile robot, and demonstrate that our method leads to a smooth exploration and high-quality reconstruction of unknown indoor scenes.

show abstract

“…Therefore. previous work on autonomous 3D modeling [20] and object recognition [21] is extended and combined. The autonomous object modeling is extended to multiple objects, and sped up by the recognition of objects that are already known.…”

Section: Scene Explorationmentioning

confidence: 99%

“…The PVS is represented by an octree, where the probability distribution of occupied/free locations is modeled. All measurements from the 3D camera and the laser striper update the probability p v (0.0 free, 0.5 unknown, 1.0 occupied) of each intersected voxel with Bayes' Rule as in [20].…”

Section: A Explorationmentioning

confidence: 99%

Combining object modeling and recognition for active scene exploration

Kriegel

Brucker

Márton

et al. 2013

2013 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

Active scene exploration incorporates object recognition methods for analyzing a scene of partially known objects and exploration approaches for autonomous modeling of unknown parts. In this work, recognition, exploration, and planning methods are extended and combined in a single scene exploration system, enabling advanced techniques such as multi-view recognition from planned view positions and iterative recognition by integration of new objects from a scene. Here, a geometry based approach is used for recognition, i.e. matching objects from a database. Unknown objects are autonomously modeled and added to the recognition database. Next-Best-View planning is performed both for recognition and modeling. Moreover, 3D measurements are merged in a Probabilistic Voxel Space, which is utilized for planning collision free paths, minimal occlusion views, and verifying the poses of the recognized objects against all previous information. Experiments on an industrial robot with attached 3D sensors are shown for scenes with household and industrial objects.

show abstract

Next-best-scan planning for autonomous 3D modeling

Cited by 46 publications

References 17 publications

Tree-based search of the next best view/state for three-dimensional object reconstruction

Tree-based search of the next best view/state for three-dimensional object reconstruction

Autonomous reconstruction of unknown indoor scenes guided by time-varying tensor fields

Combining object modeling and recognition for active scene exploration

Contact Info

Product

Resources

About