Knowledge representation in autonomous robots with social roles has steadily gained
importance through their supportive task assistance in domestic, hospital, and industrial …

Representations are crucial for a robot to learn effective navigation policies. Recent work
has shown that mid-level perceptual abstractions, such as depth estimates or 2D semantic …

Despite the enormous progress and generalization in robotic gras** in recent years,
existing methods have yet to scale and generalize task-oriented gras** to the same …

In recent years, there has been a resurgence in methods that use distributed (neural)
representations to represent and reason about semantic knowledge for robotics …

One of the big challenges in robotics is the generalization necessary for performing
unknown tasks in unknown environments on unknown objects. For us humans, this …

Robots operating in everyday environments need to effectively perceive, model, and infer
semantic properties of objects. Existing knowledge reasoning frameworks only model binary …

Semantic gras** aims to make stable robotic grasps suitable for specific object
manipulation tasks. While existing semantic gras** models focus only on the gras** …

Intelligent service robots require the ability to perform a variety of tasks in dynamic
environments. Despite the significant progress in robotic gras**, it is still a challenge for …

Requiring multiple demonstrations of a task plan presents a burden to end-users of robots.
However, robustly executing tasks plans from a single end-user demonstration is an …

Deep neural networks for graphs have emerged as a powerful tool for learning on complex
non-euclidean data, which is becoming increasingly common for a variety of different …