Related papers: Body Transformer: Leveraging Robot Embodiment for …
A clear understanding of where humans move in a scenario, their usual paths and speeds, and where they stop, is very important for different applications, such as mobility studies in urban areas or robot navigation tasks within…
Good pre-trained visual representations could enable robots to learn visuomotor policy efficiently. Still, existing representations take a one-size-fits-all-tasks approach that comes with two important drawbacks: (1) Being completely…
Recent developments in Large Language Models pre-trained on extensive corpora have shown significant success in various natural language processing tasks with minimal fine-tuning. This success offers new promise for robotics, which has long…
During the last years, many advances have been made in tasks like3D model retrieval, 3D model classification, and 3D model segmentation.The typical 3D representations such as point clouds, voxels, and poly-gon meshes are mostly suitable for…
Today's robots attempt to learn new tasks by imitating human examples. These robots watch the human complete the task, and then try to match the actions taken by the human expert. However, this standard approach to visual imitation learning…
A few decades of work in the AI field have focused efforts on developing a new generation of systems which can acquire knowledge via interaction with the world. Yet, until very recently, most such attempts were underpinned by research which…
The advancement of robots, particularly those functioning in complex human-centric environments, relies on control solutions that are driven by machine learning. Understanding how learning-based controllers make decisions is crucial since…
Physical intelligence holds immense promise for advancing embodied intelligence, enabling robots to acquire complex behaviors from demonstrations. However, achieving generalization and transfer across diverse robotic platforms and…
Continual adaptation is essential for general autonomous agents. For example, a household robot pretrained with a repertoire of skills must still adapt to unseen tasks specific to each household. Motivated by this, building upon…
Different subsystems of organisms adapt over many time scales, such as rapid changes in the nervous system (learning), slower morphological and neurological change over the lifetime of the organism (postnatal development), and change over…
Robotic manipulation can be formulated as inducing a sequence of spatial displacements: where the space being moved can encompass an object, part of an object, or end effector. In this work, we propose the Transporter Network, a simple…
Many-body descriptors are widely used to represent atomic environments in the construction of machine learned interatomic potentials and more broadly for fitting, classification and embedding tasks on atomic structures. It was generally…
The physical design of a robot suggests expectations of that robot's functionality for human users and collaborators. When those expectations align with the true capabilities of the robot, interaction with the robot is enhanced. However,…
We seek to understand how the representations of individual tokens and the structure of the learned feature space evolve between layers in deep neural networks under different learning objectives. We focus on the Transformers for our…
Recent literature shows that large-scale language modeling provides excellent reusable sentence representations with both recurrent and self-attentive architectures. However, there has been less clarity on the commonalities and differences…
Human infants learn language while interacting with their environment in which their caregivers may describe the objects and actions they perform. Similar to human infants, artificial agents can learn language while interacting with their…
Interactive adaptive systems powered by Reinforcement Learning (RL) have many potential applications, such as intelligent tutoring systems. In such systems there is typically an external human system designer that is creating, monitoring…
Transformers have become the dominant model in natural language processing, owing to their ability to pretrain on massive amounts of data, then transfer to smaller, more specific tasks via fine-tuning. The Vision Transformer was the first…
In this paper, we introduce a model of evolution and learning in robots that co-optimizes a distribution of latent design vectors (genotypes) and a mixture of control experts (neural modules), which are gated by the latent coordinates of…
Institutional and social barriers in higher education often prevent students with disabilities from effectively accessing support, including lengthy procedures, insufficient information, and high social-emotional demands. This study…