Best Viewpoint Tracking for Camera Mounted on Robotic Arm with Dynamic Obstacles

Tyleček, Radim

doi:10.1109/3dv.2017.00022

Cited by 5 publications

(7 citation statements)

References 13 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methods for proposing and selecting next best views are often tied to the representation used. Volumetric-based approaches [3,5,[11][12][13][14][15][16][17][18] commonly evaluate scene visibility by raycasting their voxel grid from proposed views to determine which voxels are observable. These algorithms typically quantify view quality based on the number of visible voxels and measurement density within each voxel.…”

Section: A Volumetric Approachesmentioning

confidence: 99%

Proactive Estimation of Occlusions and Scene Coverage for Planning Next Best Views in an Unstructured Representation

Border,

Gammell

2020

Preprint

View full text Add to dashboard Cite

The process of planning views to observe a scene is known as the Next Best View (NBV) problem. Approaches often aim to obtain high-quality scene observations while reducing the number of views, travel distance and computational cost.Considering occlusions and scene coverage can significantly reduce the number of views and travel distance required to obtain an observation. Structured representations (e.g., a voxel grid or surface mesh) typically use raycasting to evaluate the visibility of represented structures but this is often computationally expensive. Unstructured representations (e.g., point density) avoid the computational overhead of maintaining and raycasting a structure imposed on the scene but as a result do not proactively predict the success of future measurements.This paper presents proactive solutions for handling occlusions and considering scene coverage with an unstructured representation. Their performance is evaluated by extending the density-based Surface Edge Explorer (SEE). Experiments show that these techniques allow an unstructured representation to observe scenes with fewer views and shorter distances while retaining high observation quality and low computational cost.

show abstract

Section: A Volumetric Approachesmentioning

confidence: 99%

Proactive Estimation of Occlusions and Scene Coverage for Planning Next Best Views in an Unstructured Representation

Border,

Gammell

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Whenever there is an unreliable detection, the secondary camera should be planned to be moved to a proper pose to have a clear view of the object. Unlike the works [9][10][11], the proposed pose planning method is not designed for a mobile robot. Instead, we are assuming that the robot only moves its arm and the camera mounted on it to get a new viewpoint of an object.…”

Section: The Pose Plannermentioning

confidence: 99%

“…Instead, we are assuming that the robot only moves its arm and the camera mounted on it to get a new viewpoint of an object. On the other hand, to compute the arm camera pose, our method, in contrast to the analytical methods of [9][10][11], is solely dependent on the deterministic computation of robot arm joints through geometric triangulation. Our strategy to determine the joint angles of the robot arm is to have a side view of objects with the secondary camera that is almost orthogonal to the primary view.…”

Section: The Pose Plannermentioning

confidence: 99%

See 1 more Smart Citation

Active Eye-in-Hand Data Management to Improve the Robotic Object Detection Performance

et al. 2019

View full text Add to dashboard Cite

Adding to the number of sources of sensory information can be efficacious in enhancing the object detection capability of robots. In the realm of vision-based object detection, in addition to improving the general detection performance, observing objects of interest from different points of view can be central to handling occlusions. In this paper, a robotic vision system is proposed that constantly uses a 3D camera, while actively switching to make use of a second RGB camera in cases where it is necessary. The proposed system detects objects in the view seen by the 3D camera, which is mounted on a humanoid robot’s head, and computes a confidence measure for its recognitions. In the event of low confidence regarding the correctness of the detection, the secondary camera, which is installed on the robot’s arm, is moved toward the object to obtain another perspective of the object. With the objects detected in the scene viewed by the hand camera, they are matched to the detections of the head camera, and subsequently, their recognition decisions are fused together. The decision fusion method is a novel approach based on the Dempster–Shafer evidence theory. Significant improvements in object detection performance are observed after employing the proposed active vision system.

show abstract

“…However, in [8] statistically and dynamically unbalanced objects (half full bottles or a racket) are used, hence they readjust the near future predicted target position iteratively. Other approaches solve occlusion problems using using multiple cameras in the environment, such as the work of Maniatis et al [9] where they fuse multiple RGBD sensors around the arm, creating an occupancy space to find empty areas where a robot-mounted camera could be placed.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Multi-camera Visual Servoing to Moving Target

Cuevas-Velasquez

Tyleček

et al. 2018

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

Self Cite

View full text Add to dashboard Cite

Visual servoing is a well-known task in robotics. However, there are still challenges when multiple visual sources are combined to accurately guide the robot or occlusions appear. In this paper we present a novel visual servoing approach using hybrid multi-camera input data to lead a robot arm accurately to dynamically moving target points in the presence of partial occlusions. The approach uses four RGBD sensors as Eye-to-Hand (EtoH) visual input, and an arm-mounted stereo camera as Eye-in-Hand (EinH). A Master supervisor task selects between using the EtoH or the EinH, depending on the distance between the robot and target. The Master also selects the subset of EtoH cameras that best perceive the target. When the EinH sensor is used, if the target becomes occluded or goes out of the sensor's view-frustum, the Master switches back to the EtoH sensors to re-track the object. Using this adaptive visual input data, the robot is then controlled using an iterative planner that uses position, orientation and joint configuration to estimate the trajectory. Since the target is dynamic, this trajectory is updated every time-step. Experiments show good performance in four different situations: tracking a ball, targeting a bulls-eye, guiding a straw to a mouth and delivering an item to a moving hand. The experiments cover both simple situations such as a ball that is mostly visible from all cameras, and more complex situations such as the mouth which is partially occluded from some of the sensors.

show abstract

Best Viewpoint Tracking for Camera Mounted on Robotic Arm with Dynamic Obstacles

Cited by 5 publications

References 13 publications

Proactive Estimation of Occlusions and Scene Coverage for Planning Next Best Views in an Unstructured Representation

Proactive Estimation of Occlusions and Scene Coverage for Planning Next Best Views in an Unstructured Representation

Active Eye-in-Hand Data Management to Improve the Robotic Object Detection Performance

Hybrid Multi-camera Visual Servoing to Moving Target

Contact Info

Product

Resources

About