Related papers: Learning Embeddings that Capture Spatial Semantics…
Globally localizing a mobile robot in a known map is often a foundation for enabling robots to navigate and operate autonomously. In indoor environments, traditional Monte Carlo localization based on occupancy grid maps is considered the…
Autonomous robots that interact with their environment require a detailed semantic scene model. For this, volumetric semantic maps are frequently used. The scene understanding can further be improved by including object-level information in…
The words of a language reflect the structure of the human mind, allowing us to transmit thoughts between individuals. However, language can represent only a subset of our rich and detailed cognitive architecture. Here, we ask what kinds of…
Depth perception is fundamental for robots to understand the surrounding environment. As the view of cognitive neuroscience, visual depth perception methods are divided into three categories, namely binocular, active, and pictorial. The…
We study zero-shot instance navigation, in which the agent navigates to a specific object without using object annotations for training. Previous object navigation approaches apply the image-goal navigation (ImageNav) task (go to the…
This work presents a modular architecture for simultaneous mapping and target driven navigation in indoors environments. The semantic and appearance stored in 2.5D map is distilled from RGB images, semantic segmentation and outputs of…
Object rearrangement has recently emerged as a key competency in robot manipulation, with practical solutions generally involving object detection, recognition, grasping and high-level planning. Goal-images describing a desired scene…
We propose a novel robotic system that can improve its perception during deployment. Contrary to the established approach of learning semantics from large datasets and deploying fixed models, we propose a framework in which semantic models…
Zero-shot learning has gained popularity due to its potential to scale recognition models without requiring additional training data. This is usually achieved by associating categories with their semantic information like attributes.…
Enabling robots to efficiently search for and identify objects in complex, unstructured environments is critical for diverse applications ranging from household assistance to industrial automation. However, traditional scene representations…
The small objects in images and videos are usually not independent individuals. Instead, they more or less present some semantic and spatial layout relationships with each other. Modeling and inferring such intrinsic relationships can…
To autonomously navigate in real-world environments, special in search and rescue operations, Unmanned Aerial Vehicles (UAVs) necessitate comprehensive maps to ensure safety. However, the prevalent metric map often lacks semantic…
This paper presents the behaviour control of a service robot for intelligent object search in a domestic environment. A major challenge in service robotics is to enable fetch-and-carry missions that are satisfying for the user in terms of…
Robust obstacle avoidance is one of the critical steps for successful goal-driven indoor navigation tasks.Due to the obstacle missing in the visual image and the possible missed detection issue, visual image-based obstacle avoidance…
Recent studies have demonstrated the usefulness of contextualized word embeddings in unsupervised semantic frame induction. However, they have also revealed that generic contextualized embeddings are not always consistent with human…
It is challenging for humans -- particularly those living with physical disabilities -- to control high-dimensional, dexterous robots. Prior work explores learning embedding functions that map a human's low-dimensional inputs (e.g., via a…
Manipulation in cluttered environments is challenging due to spatial dependencies among objects, where an improper manipulation order can cause collisions or blocked access. Existing approaches often overlook these spatial relationships,…
Pre-trained word embeddings are widely used for transfer learning in natural language processing. The embeddings are continuous and distributed representations of the words that preserve their similarities in compact Euclidean spaces.…
The focus of past machine learning research for Reading Comprehension tasks has been primarily on the design of novel deep learning architectures. Here we show that seemingly minor choices made on (1) the use of pre-trained word embeddings,…
Leveraging class semantic descriptions and examples of known objects, zero-shot learning makes it possible to train a recognition model for an object class whose examples are not available. In this paper, we propose a novel zero-shot…