Related papers: Knowledge Retrieval using Functional Object-Orient…

We propose the object-oriented networking (OON) framework, for meeting the generalized interconnection, mobility and technology integration requirements underlining the Internet. In OON, the various objects that need to be accessed through…

This paper describes our recent research effort to bring the computer intelligence into the physical world so that robots could perform physically interactive manipulation tasks. Our proposed approach first gives robots the ability to learn…

This paper addresses the Object Goal Navigation problem, where a robot must efficiently find a target object in an unknown environment. Existing implicit memory-based methods struggle with long-term memory retention and planning, while…

Using the Functional Object-Oriented Network, we have implemented three search algorithms for generating the task trees for the given goal nodes. The approach, process, and results are written in this paper.

The ability to navigate like a human towards a language-guided target from anywhere in a 3D embodied environment is one of the 'holy grail' goals of intelligent robots. Most visual navigation benchmarks, however, focus on navigating toward…

Acquisition and creation of 3D assets have been largely view- or appearance-driven. As a result, existing digital 3D models often lack the requisite structural components to function as intended, such as joints, supports, interiors, or…

Video understanding is one of the most challenging topics in computer vision. In this paper, a four-stage video understanding pipeline is presented to simultaneously recognize all atomic actions and the single on-going activity in a video.…

The representation of the knowledge needed by a robot to perform complex tasks is restricted by the limitations of perception. One possible way of overcoming this situation and designing "knowledgeable" robots is to rely on the interaction…

A major component for developing intelligent and autonomous robots is a suitable knowledge representation, from which a robot can acquire knowledge about its actions or world. However, unlike humans, robots cannot creatively adapt to novel…

We have designed three search methods for producing the task trees for the provided goal nodes using the Functional Object-Oriented Network. This paper details the strategy, the procedure, and the outcomes.

Network embedding aims to find a way to encode network by learning an embedding vector for each node in the network. The network often has property information which is highly informative with respect to the node's position and role in the…

Most action recognition models treat human activities as unitary events. However, human activities often follow a certain hierarchy. In fact, many human activities are compositional. Also, these actions are mostly human-object interactions.…

Mathematical optimization is widely used in various research fields. With a carefully-designed objective function, mathematical optimization can be quite helpful in solving many problems. However, objective functions are usually…

Object detection and data association are critical components in multi-object tracking (MOT) systems. Despite the fact that the two components are dependent on each other, prior works often design detection and data association modules…

This paper addresses the problem of object-goal navigation in autonomous inspections in real-world environments. Object-goal navigation is crucial to enable effective inspections in various settings, often requiring the robot to identify…

Multi-task learning of deformable object manipulation is a challenging problem in robot manipulation. Most previous works address this problem in a goal-conditioned way and adapt goal images to specify different tasks, which limits the…

Graph neural networks (GNNs), as a group of powerful tools for representation learning on irregular data, have manifested superiority in various downstream tasks. With unstructured texts represented as concept maps, GNNs can be exploited…

State-of-the-art approaches to ObjectGoal navigation rely on reinforcement learning and typically require significant computational resources and time for learning. We propose Potential functions for ObjectGoal Navigation with…

Federated learning enables multiple parties to collaboratively train a machine learning model without communicating their local data. A key challenge in federated learning is to handle the heterogeneity of local data distribution across…

Object reconstruction is an important task in many fields of application as it allows to generate digital representations of our physical world used as base for analysis, planning, construction, visualization or other aims. A reconstruction…