Related papers: Reusable Slotwise Mechanisms
Video anomaly detection is a challenging task due to the lack in approaches for representing samples. The visual representations of most existing approaches are limited by short-term sequences of observations which cannot provide enough…
Moving objects to find a fully-occluded target object, known as mechanical search, is a challenging problem in robotics. As objects are often organized semantically, we conjecture that semantic information about object relationships can…
Multi-agent motion prediction is challenging because it aims to foresee the future trajectories of multiple agents (\textit{e.g.} pedestrians) simultaneously in a complicated scene. Existing work addressed this challenge by either learning…
In everyday life, frequently used objects like cups often have unfixed positions and multiple instances within the same category, and their carriers frequently change as well. As a result, it becomes challenging for a robot to efficiently…
Predictive models have been at the core of many robotic systems, from quadrotors to walking robots. However, it has been challenging to develop and apply such models to practical robotic manipulation due to high-dimensional sensory…
Response Surface Methodology (RSM) introduced in the paper (Box & Wilson, 1951) explores the relationships between explanatory and response variables in complex settings and provides a framework to identify correct settings for the…
Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency. \textit{Objects} provide a succinct and causal description of the world, and many…
The assumption of scene rigidity is common in visual SLAM algorithms. However, it limits their applicability in populated real-world environments. Furthermore, most scenarios including autonomous driving, multi-robot collaboration and…
Spatiotemporal predictive learning, which predicts future frames through historical prior knowledge with the aid of deep learning, is widely used in many fields. Previous work essentially improves the model performance by widening or…
Autonomous systems face the intricate challenge of navigating unpredictable environments and interacting with external objects. The successful integration of robotic agents into real-world situations hinges on their perception capabilities,…
This paper introduces the concept of Language-Guided World Models (LWMs) -- probabilistic models that can simulate environments by reading texts. Agents equipped with these models provide humans with more extensive and efficient control,…
Capturing scene dynamics and predicting the future scene state is challenging but essential for robotic manipulation tasks, especially when the scene contains both rigid and deformable objects. In this work, we contribute a simulation…
In this paper, we propose an adaptive keyframe selection method for improved 3D scene reconstruction in dynamic environments. The proposed method integrates two complementary modules: an error-based selection module utilizing photometric…
Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the…
Modeling instance-level context and object-object relationships is extremely challenging. It requires reasoning about bounding boxes of different classes, locations \etc. Above all, instance-level spatial reasoning inherently requires…
We propose RecSim, a configurable platform for authoring simulation environments for recommender systems (RSs) that naturally supports sequential interaction with users. RecSim allows the creation of new environments that reflect particular…
Dynamical systems with complex behaviours, e.g. immune system cells interacting with a pathogen, are commonly modelled by splitting the behaviour into different regimes, or modes, each with simpler dynamics, and then learning the switching…
Motion planning in environments with multiple agents is critical to many important autonomous applications such as autonomous vehicles and assistive robots. This paper considers the problem of motion planning, where the controlled agent…
State-space models (SSMs) offer a powerful framework for dynamical system analysis, wherein the temporal dynamics of the system are assumed to be captured through the evolution of the latent states, which govern the values of the…
Object SLAM is considered increasingly significant for robot high-level perception and decision-making. Existing studies fall short in terms of data association, object representation, and semantic mapping and frequently rely on additional…