Related papers: From explanation to synthesis: Compositional progr…
The objective of this work is to augment the basic abilities of a robot by learning to use sensorimotor primitives to solve complex long-horizon manipulation problems. This requires flexible generative planning that can combine primitive…
The goal of program synthesis from examples is to find a computer program that is consistent with a given set of input-output examples. Most learning-based approaches try to find a program that satisfies all examples at once. Our work, by…
According to the principle of compositional generalization, the meaning of a complex expression can be understood as a function of the meaning of its parts and of how they are combined. This principle is crucial for human language…
To solve a new task from minimal experience, it is essential to effectively reuse knowledge from previous tasks, a problem known as meta-learning. Compositional solutions, where common elements of computation are flexibly recombined into…
Controller synthesis, including reset controller, feedback controller, and switching logic controller, provides an essential mechanism to guarantee the correctness and reliability of hybrid systems in a correct-by-construction manner.…
Collecting robotic manipulation data is expensive, making it impractical to acquire demonstrations for the combinatorially large space of tasks that arise in multi-object, multi-robot, and multi-environment settings. While recent generative…
Humans are highly efficient learners, with the ability to grasp the meaning of a new concept from just a few examples. Unlike popular computer vision systems, humans can flexibly leverage the compositional structure of the visual world,…
While machine learning can accurately model process systems, models for decision making should also be structurally simple and physically interpretable. In process control, for example, (nearly) linear models are favored than nonlinear…
Modular robots can be reconfigured to create a variety of designs from a small set of components. But constructing a robot's hardware on its own is not enough -- each robot needs a controller. One could create controllers for some designs…
Our goal is to build systems which write code automatically from the kinds of specifications humans can most easily provide, such as examples and natural language instruction. The key idea of this work is that a flexible combination of…
In this paper we propose a compositional framework for the construction of approximations of the interconnection of a class of stochastic hybrid systems. As special cases, this class of systems includes both jump linear stochastic systems…
Leveraging the compositional nature of our world to expedite learning and facilitate generalization is a hallmark of human perception. In machine learning, on the other hand, achieving compositional generalization has proven to be an…
In-context learning has shown great success in i.i.d semantic parsing splits, where the training and test sets are drawn from the same distribution. In this setup, models are typically prompted with demonstrations that are similar to the…
Robotic research over the last decades have lead us to different architectures to automatically synthesise discrete event controllers and implement these motion and task plans in real-world robot scenarios. However, these architectures…
We introduce a novel formulation for incorporating visual feedback in controlling robots. We define a generative model from actions to image observations of features on the end-effector. Inference in the model allows us to infer the robot…
Transformers have demonstrated impressive capabilities across various tasks, yet their performance on compositional problems remains a subject of debate. In this study, we investigate the internal mechanisms underlying Transformers'…
Imitation learning is an effective approach for autonomous systems to acquire control policies when an explicit reward function is unavailable, using supervision provided as demonstrations from an expert, typically a human operator.…
Hybrid learning methods use theoretical knowledge of a domain and a set of classified examples to develop a method for classification. Methods that use domain knowledge have been shown to perform better than inductive learners. However,…
A common approach in robotics is to learn tasks by generalizing from special cases given by a so-called demonstrator. In this paper, we apply this paradigm and present an algorithm that uses a demonstrator (typically given by a trajectory…
Compositional automata learning is attracting attention as an analysis technique for complex black-box systems. It exploits a target system's internal compositional structure to reduce complexity. In this paper, we identify system…