3D object perception and perceptual learning in the RACE project

Oliveira, Miguel; Lopes, Luís Seabra; Lim, Gi Hyun; Kasaei, S. Hamidreza; Tomé, Ana Maria; Chauhan, Aneesh

doi:10.1016/j.robot.2015.09.019

Cited by 38 publications

(34 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Object Detection launches a new object perception pipeline for each detected object and pushes the object's point cloud to the pipeline [29]. Object Tracking receives the point cloud of the detected object, computes an oriented bounding box and estimates the current pose of the object based on a particle filter, which uses shape and color data [12] (see Fig. 7 left).…”

Section: B Perceptual Learning and Recognitionmentioning

confidence: 99%

Interactive Open-Ended Object, Affordance and Grasp Learning for Robotic Manipulation

Kasaei

Shafii

Lopes

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Service robots are expected to autonomously and efficiently work in human-centric environments. For this type of robots, object perception and manipulation are challenging tasks due to need for accurate and real-time response. This paper presents an interactive open-ended learning approach to recognize multiple objects and their grasp affordances concurrently. This is an important contribution in the field of service robots since no matter how extensive the training data used for batch learning, a robot might always be confronted with an unknown object when operating in human-centric environments. The paper describes the system architecture and the learning and recognition capabilities. Grasp learning associates grasp configurations (i.e., end-effector positions and orientations) to grasp affordance categories. The grasp affordance category and the grasp configuration are taught through verbal and kinesthetic teaching, respectively. A Bayesian approach is adopted for learning and recognition of object categories and an instance-based approach is used for learning and recognition of affordance categories. An extensive set of experiments has been performed to assess the performance of the proposed approach regarding recognition accuracy, scalability and grasp success rate on challenging datasets and real-world scenarios.All authors are with IEETA -University of Aveiro, 3810-193, Aveiro, Portugal. S. Hamidreza Kasaei is also with

show abstract

Section: B Perceptual Learning and Recognitionmentioning

confidence: 99%

Interactive Open-Ended Object, Affordance and Grasp Learning for Robotic Manipulation

Kasaei

Shafii

Lopes

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the last decade, various research groups have made substantial progress towards the development of learning approaches which support online and incremental object category learning [1] [2]. In recent studies on object recognition, much attention has been given to deep Convolutional Neural Networks (CNNs [6] allows for concurrent learning and recognition.…”

Section: Related Workmentioning

confidence: 99%

“…For comparison, we have selected four open-ended 3D object category learning and recognition approaches, including the RACE [1], BoW [18] based on the nearest neighbour classification rule, and Open-Ended LDA, which is a modified version of the standard smoothed LDA [19] and Local-LDA [5]. Moreover, we add another baseline, which is the proposed method without category-specific representation (here referred to as Generic Rep.).…”

Section: A Datasets and Baselinesmentioning

confidence: 99%

See 1 more Smart Citation

Look Further to Recognize Better: Learning Shared Topics and Category-Specific Dictionaries for Open-Ended 3D Object Recognition

Kasaei

2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

Service robots are expected to operate effectively in human-centric environments for long periods of time. In such realistic scenarios, fine-grained object categorization is as important as basic-level object categorization. We tackle this problem by proposing an open-ended object recognition approach which concurrently learns both the object categories and the local features for encoding objects. In this work, each object is represented using a set of general latent visual topics and category-specific dictionaries. The general topics encode the common patterns of all categories, while the category-specific dictionary describes the content of each category in details. The proposed approach discovers both sets of general and specific representations in an unsupervised fashion and updates them incrementally using new object views. Experimental results show that our approach yields significant improvements over the previous state-of-the-art approaches concerning scalability and object classification performance. Moreover, our approach demonstrates the capability of learning from very few training examples in a real-world setting. Regarding computation time, the best result was obtained with a Bag-of-Words method followed by a variant of the Latent Dirichlet Allocation approach.

show abstract

“…In the digital preservation area, visually aesthetic and detailed 3D models of buildings and historical cities are generated by laser scanning and digital photogrammetry [1,2]. In the robotics area, point clouds are used to recognize the identity, pose, and location of the target object and obstacles for robot movement and manipulation [3,4].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning on Point Clouds and Its Application: A Survey

Liu

Sun

et al. 2019

Sensors

187

View full text Add to dashboard Cite

Point cloud is a widely used 3D data form, which can be produced by depth sensors, such as Light Detection and Ranging (LIDAR) and RGB-D cameras. Being unordered and irregular, many researchers focused on the feature engineering of the point cloud. Being able to learn complex hierarchical structures, deep learning has achieved great success with images from cameras. Recently, many researchers have adapted it into the applications of the point cloud. In this paper, the recent existing point cloud feature learning methods are classified as point-based and tree-based. The former directly takes the raw point cloud as the input for deep learning. The latter first employs a k-dimensional tree (Kd-tree) structure to represent the point cloud with a regular representation and then feeds these representations into deep learning models. Their advantages and disadvantages are analyzed. The applications related to point cloud feature learning, including 3D object classification, semantic segmentation, and 3D object detection, are introduced, and the datasets and evaluation metrics are also collected. Finally, the future research trend is predicted.

show abstract

3D object perception and perceptual learning in the RACE project

Cited by 38 publications

References 28 publications

Interactive Open-Ended Object, Affordance and Grasp Learning for Robotic Manipulation

Interactive Open-Ended Object, Affordance and Grasp Learning for Robotic Manipulation

Look Further to Recognize Better: Learning Shared Topics and Category-Specific Dictionaries for Open-Ended 3D Object Recognition

Deep Learning on Point Clouds and Its Application: A Survey

Contact Info

Product

Resources

About