Publicaties

Motion prediction of the human pose estimates future poses based on the preceding poses. It is a stepping stone toward industrial applications, like human-robot interactions and ergonomy indicators. The goal is to minimize the error in predicted joint positions on the IKEA-ASM dataset which resembles assembly use cases with a high diversity of execution and background of the same action class. In this paper, we use the STS- GCN model to tackle ...

We present a multi-modal AI framework to intuitively instruct and control Automated Guided Vehicles. We define a general multi-modal AI architecture, which has a loose coupling between three different AI modules, including spoken language understanding, visual perception and Reinforcement Learning navigation. We use the same multi-modal architecture for two different use cases implemented in two different platforms: an off-road vehicle, which ...

Reinforcement learning (RL) algorithms typically start tabula rasa, without any prior knowledge of the environment, and without any prior skills. This however often leads to low sample efficiency, requiring a large amount of interaction with the environment. This is especially true in a lifelong learning setting, in which the agent needs to continually extend its capabilities. In this paper, we examine how a pre-trained task-independent language ...

Reinforcement learning (RL) allows an agent to solve sequential decision-making problems by interacting with an environment in a trial-and-error fashion. When these environments are very complex, pure random exploration of possible solutions often fails, or is very sample inefficient, requiring an unreasonable amount of interaction with the environment. Hierarchical reinforcement learning (HRL) utilizes forms of temporal- and state-abstractions ...

Over its lifetime, a Reinforcement Learning agent is often instructed to perform dierent tasks. How to eciently adapt a previously learned control policy from one task to another, remains an open research question. In this paper, we investigate how instructions formulated in natural language can enable faster and more eective task adaptation. Our proposed method is capable of assessing, given a set of developed base control policies, which base ...

Embodied AI, learning through interaction with a physical environment, typically requires large amounts of interaction with the environment in order to learn how to solve new tasks. Training can be done in parallel, using simulated environments. However, once deployed in e.g., a real-world setting, it is not yet clear how an agent can quickly adapt its knowledge to solve new tasks. In this paper, we propose a novel Hierarchical Reinforcement ...

In current production shop floors, a fleet of production machines and AGVs form a full manufacturing system with a high degree of automation. These current manufacturing systems need to deal with high variability of products and production tasks. Every task, however, requires a proper reconfiguration & control that is often done manually requiring complex settings and long configuration time. With AI techniques the reconfiguration of these ...