相关论文: Back to Reality for Imitation Learning

Imitation learning is a popular paradigm to teach robots new tasks, but collecting robot demonstrations through teleoperation or kinesthetic teaching is tedious and time-consuming. In contrast, directly demonstrating a task using our human…

Robots today often miss a key ingredient of truly intelligent behavior: the ability to reflect on their own cognitive processes and decisions. In humans, this self-monitoring or metacognition is crucial for learning, decision making and…

Imitation from observation is the framework of learning tasks by observing demonstrated state-only trajectories. Recently, adversarial approaches have achieved significant performance improvements over other methods for imitating complex…

Humans can leverage hierarchical structures to split a task into sub-tasks and solve problems efficiently. Both imitation and reinforcement learning or a combination of them with hierarchical structures have been proven to be an efficient…

Lack of reliability is a well-known issue for reinforcement learning (RL) algorithms. This problem has gained increasing attention in recent years, and efforts to improve it have grown substantially. To aid RL researchers and production…

The concept of the value-gradient is introduced and developed in the context of reinforcement learning. It is shown that by learning the value-gradients exploration or stochastic behaviour is no longer needed to find locally optimal…

Reinforcement learning (RL) has become widely adopted in robot control. Despite many successes, one major persisting problem can be very low data efficiency. One solution is interactive feedback, which has been shown to speed up RL…

Many existing imitation learning datasets are collected from multiple demonstrators, each with different expertise at different parts of the environment. Yet, standard imitation learning algorithms typically treat all demonstrators as…

Imitation learning stands at a crossroads: despite decades of progress, current imitation learning agents remain sophisticated memorisation machines, excelling at replay but failing when contexts shift or goals evolve. This paper argues…

While visual imitation learning offers one of the most effective ways of learning from visual demonstrations, generalizing from them requires either hundreds of diverse demonstrations, task specific priors, or large, hard-to-train…

Reinforcement learning has emerged as a promising methodology for training robot controllers. However, most results have been limited to simulation due to the need for a large number of samples and the lack of automated-yet-safe data…

World models, which are predictive representations of how environments evolve under actions, have become a central component of robot learning. They support policy learning, planning, simulation, evaluation, data generation, and have…

Navigation is one of the most heavily studied problems in robotics, and is conventionally approached as a geometric mapping and planning problem. However, real-world navigation presents a complex set of physical challenges that defies…

Construction robots are challenging the traditional paradigm of labor intensive and repetitive construction tasks. Present concerns regarding construction robots are focused on their abilities in performing complex tasks consisting of…

In this work we propose a novel end-to-end imitation learning approach which combines natural language, vision, and motion information to produce an abstract representation of a task, which in turn is used to synthesize specific motion…

Learning Machines is developing a flexible, cross-industry, advanced analytics platform, targeted during stealth-stage at a limited number of specific vertical applications. In this paper, we aim to integrate a general machine system to…

This paper argues that Machine Learning (ML) algorithms must be educated. ML-trained algorithms moral decisions are ubiquitous in human society. Sometimes reverting the societal advances governments, NGOs and civil society have achieved…

Humans can leverage physical interaction to teach robot arms. This physical interaction takes multiple forms depending on the task, the user, and what the robot has learned so far. State-of-the-art approaches focus on learning from a single…

Embodied learning for object-centric robotic manipulation is a rapidly developing and challenging area in embodied AI. It is crucial for advancing next-generation intelligent robots and has garnered significant interest recently. Unlike…

Quadruped robots have emerged as an evolving technology that currently leverages simulators to develop a robust controller capable of functioning in the real-world without the need for further training. However, since it is impossible to…