相关论文: Goal-Space Planning with Subgoal Models

Sequential decision making, commonly formalized as Markov Decision Process (MDP) optimization, is a important challenge in artificial intelligence. Two key approaches to this problem are reinforcement learning (RL) and planning. This paper…

Planning robust robot manipulation requires good forward models that enable robust plans to be found. This work shows how to achieve this using a forward model learned from robot data to plan push manipulations. We explore learning methods…

We focus on the task of goal-oriented grasping, in which a robot is supposed to grasp a pre-assigned goal object in clutter and needs some pre-grasp actions such as pushes to enable stable grasps. However, in this task, the robot gets…

Stable dynamical systems are a flexible tool to plan robotic motions in real-time. In the robotic literature, dynamical system motions are typically planned without considering possible limitations in the robot's workspace. This work…

Autonomous navigation in dynamic environments is a complex but essential task for autonomous robots. Recent deep reinforcement learning approaches show promising results to solve the problem, but it is not solved yet, as they typically…

Recent improvements in deep reinforcement learning have allowed to solve problems in many 2D domains such as Atari games. However, in complex 3D environments, numerous learning episodes are required which may be too time consuming or even…

In this paper, we propose a learning algorithm that speeds up the search in task and motion planning problems. Our algorithm proposes solutions to three different challenges that arise in learning to improve planning efficiency: what to…

Model-based reinforcement learning methods often use learning only for the purpose of estimating an approximate dynamics model, offloading the rest of the decision-making work to classical trajectory optimizers. While conceptually simple,…

Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoencoders or inverse dynamics enable goal-conditioned decision…

Generalised planning (GP) refers to the task of synthesising programs that solve families of related planning problems. We introduce a novel, yet simple method for GP: given a set of training problems, for each problem, compute an optimal…

Structured state space sequence (S4) models have recently achieved state-of-the-art performance on long-range sequence modeling tasks. These models also have fast inference speeds and parallelisable training, making them potentially useful…

Autonomous mobile robots (e.g., warehouse logistics robots) often need to traverse complex, obstacle-rich, and changing environments to reach multiple fixed goals (e.g., warehouse shelves). Traditional motion planners need to calculate the…

In goal-conditioned offline reinforcement learning, an agent learns from previously collected data to go to an arbitrary goal. Since the offline data only contains a finite number of trajectories, a main challenge is how to generate more…

Generating obstacle-free trajectories for robotic manipulators in unstructured and cluttered environments remains a significant challenge. Existing motion planning methods often require additional computational effort to generate the final…

Offline goal-conditioned reinforcement learning (GCRL) can be challenging due to overfitting to the given dataset. To generalize agents' skills outside the given dataset, we propose a goal-swapping procedure that generates additional…

Path planning for mobile robots in large dynamic environments is a challenging problem, as the robots are required to efficiently reach their given goals while simultaneously avoiding potential conflicts with other robots or dynamic…

In many real world applications, reinforcement learning agents have to optimize multiple objectives while following certain rules or satisfying a list of constraints. Classical methods based on reward shaping, i.e. a weighted combination of…

We review current and emerging knowledge-informed and brain-inspired cognitive systems for realizing adversarial defenses, eXplainable Artificial Intelligence (XAI), and zero-shot or few-short learning. Data-driven deep learning models have…

Robot motion planning involves computing a sequence of valid robot configurations that take the robot from its initial state to a goal state. Solving a motion planning problem optimally using analytical methods is proven to be PSPACE-Hard.…

Earth observing satellites are powerful tools for collecting scientific information about our planet, however they have limitations: they cannot easily deviate from their orbital trajectories, their sensors have a limited field of view, and…