Probabilistic models for robot-based object segmentation

Beale, Daniel; Iravani, Pejman; Hall, Peter M.

doi:10.1016/j.robot.2011.08.003

Cited by 11 publications

(28 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To learn the properties of novel objects in cluttered scenes, segmenting those images is usually a required first step [6,7]. In this section, we will review various approaches to the scene segmentation problem and contrast our approach to this prior work.…”

Section: Related Workmentioning

confidence: 99%

“…Through interaction, a robot can obtain multiple views of a scene (for approaches like [18]) autonomously. Besides, knowing what action was performed helps the robot to interpret ambiguous observations, such as movement of an object of interest when there is background movement as well [7].…”

Section: B Interactive Perception For Object Segmentationmentioning

confidence: 99%

“…To estimate movement direction, a part based representation using an initial over-segmentation can be used [7]. In a subsequent stage, movement and object membership can be estimated for each of these parts.…”

Section: B Interactive Perception For Object Segmentationmentioning

confidence: 99%

“…Thus, with a limited amount of experience, there is uncertainty about the true segmentation. Many of the discussed approaches do not handle occlusion and co-movement as they deal with only one object of interest, e.g., [6,7,15]. Noise is often ignored [14,15] or handled by requiring objects to move as rigid bodies during one or multiple actions [12,16,19,33].…”

Section: Dealing With Noise and Cluttermentioning

confidence: 99%

“…hand [6,7]. Such methods should be robust to noise and uncertainty (e.g., as induced by sensor-or manipulation failures and occlusions).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Probabilistic Segmentation and Targeted Exploration of Objects in Cluttered Environments

2014

View full text Add to dashboard Cite

Abstract-Creating robots that can act autonomously in dynamic, unstructured environments requires dealing with novel objects. Thus, an off-line learning phase is not sufficient for recognizing and manipulating such objects. Rather, an autonomous robot needs to acquire knowledge through its own interaction with its environment, without using heuristics encoding human insights about the domain. Interaction also allows information that is not present in static images of a scene to be elicited. Out of a potentially large set of possible interactions, a robot must select actions that are expected to have the most informative outcomes to learn efficiently. In the proposed bottom-up, probabilistic approach, the robot achieves this goal by quantifying the expected informativeness of its own actions in information-theoretic terms. We use this approach to segment a scene into its constituent objects. We retain a probability distribution over segmentations. We show that this approach is robust in the presence of noise and uncertainty in real-world experiments. Evaluations show that the proposed information-theoretic approach allows a robot to efficiently determine the composite structure of its environment. We also show that our probabilistic model allows straightforward integration of multiple modalities, such as movement data and static scene features. Learned static scene features allow for experience from similar environments to speed up learning for new scenes.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: B Interactive Perception For Object Segmentationmentioning

confidence: 99%

Section: B Interactive Perception For Object Segmentationmentioning

confidence: 99%