Our experimental results show that PTP can generate feasible sequences of subgoals that enable the policy to efficiently solve the target tasks.
To encourage generalizable skills to emerge, our method trains each skill to specialize in the paired task and maximizes the diversity of the generated tasks.
The experimental results in simulation and on the real robot have demonstrated that the use of implicit neural representations and joint learning of grasp affordance and 3D reconstruction have led to state-of-the-art grasping results.
Search engine has become a fundamental component in various web and mobile applications.
To enable curriculum learning in the absence of a direct indicator of learning progress, we propose to train the task generator by balancing the agent's performance in the generated tasks and the similarity to the target tasks.
Recently, there are a few methods have been proposed which focused on mining information across ranking candidates list for further improvements, such as learning multivariant scoring function or learning contextual embedding.
The fundamental challenge of planning for multi-step manipulation is to find effective and plausible action sequences that lead to the task goal.
Many robotic applications require the agent to perform long-horizon tasks in partially observable environments.
We perform both simulated and real-world experiments on two tool-based manipulation tasks: sweeping and hammering.
The external memory explicitly stores previous inputs of each trajectory in a time window, while the internal memory learns to summarize long-term tracking history and associate detections by processing the external memory.
Learning-based approaches to robotic manipulation are limited by the scalability of data collection and accessibility of labels.
We consider the problem of estimating the spatial layout of an indoor scene from a monocular RGB image, modeled as the projection of a 3D cuboid.