Related papers: Arcades: A deep model for adaptive decision making…
The Abstraction and Reasoning Corpus (ARC) is designed to assess generalization beyond pattern matching, requiring models to infer symbolic rules from very few examples. In this work, we present a transformer-based system that advances ARC…
Recently developed pretrained models can encode rich world knowledge expressed in multiple modalities, such as text and images. However, the outputs of these models cannot be integrated into algorithms to solve sequential decision-making…
Intelligent agents must be able to think fast and slow to perform elaborate manipulation tasks. Reinforcement Learning (RL) has led to many promising results on a range of challenging decision-making tasks. However, in real-world robotics,…
Animals and robots exist in a physical world and must coordinate their bodies to achieve behavioral objectives. With recent developments in deep reinforcement learning, it is now possible for scientists and engineers to obtain sensorimotor…
Humans and animals show remarkable learning efficiency, adapting to new environments with minimal experience. This capability is not well captured by standard reinforcement learning algorithms that rely on incremental value updates. Rapid…
Intelligent systems have the ability to improve their behaviour over time taking observations, experiences or explicit feedback into account. Traditional approaches separate the learning problem and make isolated use of techniques from…
As learning-based methods make their way from perception systems to planning/control stacks, robot control systems have started to enjoy the benefits that data-driven methods provide. Because control systems directly affect the motion of…
Transforming sound insights into actionable streams of data, this abstract leverages findings from degree thesis research to enhance automotive system intelligence, enabling us to address road type [1].By extracting and interpreting…
Modern virtual personal assistants provide a convenient interface for completing daily tasks via voice commands. An important consideration for these assistants is the ability to recover from automatic speech recognition (ASR) and natural…
The concept of augmented reality (AR) assistants has captured the human imagination for decades, becoming a staple of modern science fiction. To pursue this goal, it is necessary to develop artificial intelligence (AI)-based methods that…
Robot Imitation Learning (IL) is a crucial technique in robot learning, where agents learn by mimicking human demonstrations. However, IL encounters scalability challenges stemming from both non-user-friendly demonstration collection…
Making the interaction with embodied conversational agents accessible in a ubiquitous and natural manner is not only a question of the underlying software but also brings challenges in terms of the technical system that is used to display…
This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract…
Deep reinforcement learning is becoming increasingly popular for robot control algorithms, with the aim for a robot to self-learn useful feature representations from unstructured sensory input leading to the optimal actuation policy. In…
This work introduces a data-driven control approach for stabilizing high-dimensional dynamical systems from scarce data. The proposed context-aware controller inference approach is based on the observation that controllers need to act…
We present an integrated approach for perception and control for an autonomous vehicle and demonstrate this approach in a high-fidelity urban driving simulator. Our approach first builds a model for the environment, then trains a policy…
A key aspect of intelligence is the ability to demonstrate a broad spectrum of behaviors for adapting to unexpected situations. Over the past decade, advancements in deep reinforcement learning have led to groundbreaking achievements to…
Cognitive sensing refers to a reconfigurable sensor that dynamically adapts its sensing mechanism by using stochastic control to optimize its sensing resources. For example, cognitive radars are sophisticated dynamical systems; they use…
We will present a new general framework for robust and adaptive control that allows for distributed and scalable learning and control of large systems of interconnected linear subsystems. The control method is demonstrated for a linear…
In machine learning, meta-learning methods aim for fast adaptability to unknown tasks using prior knowledge. Model-based meta-reinforcement learning combines reinforcement learning via world models with Meta Reinforcement Learning (MRL) for…