相关论文: Deep Spatial Autoencoders for Visuomotor Learning

We study active object tracking, where a tracker takes as input the visual observation (i.e., frame sequence) and produces the camera control signal (e.g., move forward, turn left, etc.). Conventional methods tackle the tracking and the…

Traditional visual servoing methods suffer from serving between scenes from multiple perspectives, which humans can complete with visual signals alone. In this paper, we investigated how multi-perspective visual servoing could be solved…

Motivated by the challenge of achieving rapid learning in physical environments, this paper presents the development and training of a robotic system designed to navigate and solve a labyrinth game using model-based reinforcement learning…

Dexterous manipulation has received considerable attention in recent research. Predominantly, existing studies have concentrated on reinforcement learning methods to address the substantial degrees of freedom in hand movements. Nonetheless,…

Reinforcement learning (RL) holds great promise for enabling autonomous acquisition of complex robotic manipulation skills, but realizing this potential in real-world settings has been challenging. We present a human-in-the-loop…

Humans can infer accurate mechanical outcomes from only a few observations, a capability known as mechanics intuition. The mechanisms behind such data-efficient learning remain unclear. Here, we propose a reinforcement learning framework in…

Understanding physical phenomena is a key competence that enables humans and animals to act and interact under uncertain perception in previously unseen environments containing novel objects and their configurations. In this work, we…

Humans are adept at learning new tasks by watching a few instructional videos. On the other hand, robots that learn new actions either require a lot of effort through trial and error, or use expert demonstrations that are challenging to…

Model-free reinforcement learning has recently been shown to successfully learn navigation policies from raw sensor data. In this work, we address the problem of learning driving policies for an autonomous agent in a high-fidelity…

In this paper, we address the problem of task-oriented grasping for humanoid robots, emphasizing the need to align with human social norms and task-specific objectives. Existing methods, employ a variety of open-loop and closed-loop…

Mobile manipulation tasks remain one of the critical challenges for the widespread adoption of autonomous robots in both service and industrial scenarios. While planning approaches are good at generating feasible whole-body robot…

The main novelty of the proposed approach is that it allows a robot to learn an end-to-end policy which can adapt to changes in the environment during execution. While goal conditioning of policies has been studied in the RL literature,…

To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its deployment in the…

Learning-based methods have improved locomotion skills of quadruped robots through deep reinforcement learning. However, the sim-to-real gap and low sample efficiency still limit the skill transfer. To address this issue, we propose an…

Visual features can help predict if a manipulation behavior will succeed at a given location. For example, the success of a behavior that flips light switches depends on the location of the switch. Within this paper, we present methods that…

Deep Reinforcement learning holds the guarantee of empowering self-ruling robots to master enormous collections of conduct abilities with negligible human mediation. The improvements brought by this technique enables robots to perform…

In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences.…

We address the problem of autonomously learning controllers for vision-capable mobile robots. We extend McCallum's (1995) Nearest-Sequence Memory algorithm to allow for general metrics over state-action trajectories. We demonstrate the…

We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies which can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The training is performed in a simulated environment in which we…

Model-based reinforcement learning attempts to use an available or learned model to improve the data efficiency of reinforcement learning. This work proposes a one-step lookback approach that jointly learns the deep incremental model and…