Related papers: Deictic Image Maps: An Abstraction For Learning Po…

This paper addresses the problem of learning abstractions that boost robot planning performance while providing strong guarantees of reliability. Although state-of-the-art hierarchical robot planning algorithms allow robots to efficiently…

Face inpainting requires the model to have a precise global understanding of the facial position structure. Benefiting from the powerful capabilities of deep learning backbones, recent works in face inpainting have achieved decent…

Learning generalist policies capable of accomplishing a plethora of everyday tasks remains an open challenge in dexterous manipulation. In particular, collecting large-scale manipulation data via real-world teleoperation is expensive and…

Generalizing manipulation skills to new situations requires extracting invariant patterns from demonstrations. For example, the robot needs to understand the demonstrations at a higher level while being invariant to the appearance of the…

In robotic grasping, objects are often occluded in ungraspable configurations such that no pregrasp pose can be found, eg large flat boxes on the table that can only be grasped from the side. Inspired by humans' bimanual manipulation, eg…

The focus of this work is to enumerate the various approaches and algorithms that center around application of reinforcement learning in robotic ma- ]]nipulation tasks. Earlier methods utilized specialized policy representations and human…

Skilled robot task learning is best implemented by predictive action policies due to the inherent latency of sensorimotor processes. However, training such predictive policies is challenging as it involves finding a trajectory of motor…

State-of-the-art reinforcement learning algorithms predominantly learn a policy from either a numerical state vector or images. Both approaches generally do not take structural knowledge of the task into account, which is especially…

Learning-based methods for dexterous manipulation have made notable progress in recent years. However, learned policies often still lack reliability and exhibit limited robustness to important factors of variation. One failure pattern that…

Designing reward functions that generalize beyond controlled laboratory settings remains a fundamental challenge in reinforcement learning for robotics. In open-world manipulation problems, a single task can appear in numerous variants…

Most state-of-the-art localization algorithms rely on robust relative pose estimation and geometry verification to obtain moving object agnostic camera poses in complex indoor environments. However, this approach is prone to mistakes if a…

This paper presents a hierarchical framework for Deep Reinforcement Learning that acquires motor skills for a variety of push recovery and balancing behaviors, i.e., ankle, hip, foot tilting, and stepping strategies. The policy is trained…

We present a deep imitation learning framework for robotic bimanual manipulation in a continuous state-action space. A core challenge is to generalize the manipulation skills to objects in different locations. We hypothesize that modeling…

Modeling and prediction of human motion dynamics has long been a challenging problem in computer vision, and most existing methods rely on the end-to-end supervised training of various architectures of recurrent neural networks. Inspired by…

Many practically relevant robot grasping problems feature a target object for which all grasps are occluded, e.g., by the environment. Single-shot grasp planning invariably fails in such scenarios. Instead, it is necessary to first…

In-hand manipulation with multi-fingered hands is a challenging problem that recently became feasible with the advent of deep reinforcement learning methods. While most contributions to the task brought improvements in robustness and…

The presentation and analysis of image data from a single viewpoint are often not sufficient to solve a task. Several viewpoints are necessary to obtain more information. The next-best-view problem attempts to find the optimal viewpoint…

In this paper, we explore whether a robot can learn to regrasp a diverse set of objects to achieve various desired grasp poses. Regrasping is needed whenever a robot's current grasp pose fails to perform desired manipulation tasks. Endowing…

Active inference is a first principles approach for understanding the brain in particular, and sentient agents in general, with the single imperative of minimizing free energy. As such, it provides a computational account for modelling…

State-of-the-art computer vision algorithms often achieve efficiency by making discrete choices about which hypotheses to explore next. This allows allocation of computational resources to promising candidates, however, such decisions are…