Unsupervised video-based object-centric learning is a promising avenue to learn structured representations from large, unlabeled video collections, but previous approaches have only managed to scale to real-world data...
详细信息
Fog computing offers low-latency and real-time big-data processing capabilities closer to the network edge. This particular benefit addresses the main bottleneck in a centralized cloud framework, which is, it cannot p...
详细信息
Component-based development is one of the core principles behind modern software engineering practices. Understanding of causal relationships between components of a software system can yield significant benefits to d...
详细信息
Real-world robotic manipulation tasks remain an elusive challenge, since they involve both fine-grained environment interaction, as well as the ability to plan for long-horizon goals. Although deep reinforcement learn...
Real-world robotic manipulation tasks remain an elusive challenge, since they involve both fine-grained environment interaction, as well as the ability to plan for long-horizon goals. Although deep reinforcement learning (RL) methods have shown encouraging results when planning end-to-end in high-dimensional environments, they remain fundamentally limited by poor sample efficiency due to inefficient exploration, and by the complexity of credit assignment over long horizons. In this work, we present Efficient Learning of High-Level Plans from Play (ELF-P), a framework for robotic learning that bridges motion planning and deep RL to achieve long-horizon complex manipulation tasks. We leverage task-agnostic play data to learn a discrete behavioral prior over object-centric primitives, modeling their feasibility given the current context. We then design a high-level goal-conditioned policy which (1) uses primitives as building blocks to scaffold complex long-horizon tasks and (2) leverages the behavioral prior to accelerate learning. We demonstrate that ELF-P has significantly better sample efficiency than relevant baselines over multiple realistic manipulation tasks and learns policies that can be easily transferred to physical hardware.
Real-world robotic manipulation tasks remain an elusive challenge, since they involve both fine-grained environment interaction, as well as the ability to plan for long-horizon goals. Although deep reinforcement learn...
详细信息
This literature review aimed to compare various time-series analysis approaches utilized in forecasting COVID-19 cases in Africa. The study involved a methodical search for English-language research papers published b...
详细信息
Text style transfer, an important research direction in natural language processing, aims to adapt the text to various preferences but often faces challenges with limited resources. In this work, we introduce a novel ...
The autonomous interpretation of application intent (APPI) represents the primary step towards achieving closed-loop autonomy in zero-touch networking (ZTN) and also a prerequisite for intent-based networking (IBN). H...
详细信息
作者：
Josh LuzierDavid C. ConnerDepartment of Physics
Computer Science and Engineering Capable Humanitarian Robotics and Intelligent Systems Lab (CHRISLab) Christopher Newport University Newport News Virginia
This paper presents synthesis tools for the ROS 2 version of the Flexible Behavior Engine (FlexBE). Synthesis reduces the need for extensive testing and validation of hand crafted controllers by using mathematically p...
This paper presents synthesis tools for the ROS 2 version of the Flexible Behavior Engine (FlexBE). Synthesis reduces the need for extensive testing and validation of hand crafted controllers by using mathematically precise specifications to generate “correct-by-construction” behavior controllers. Our approach builds upon work using the GR(1) (General Reactivity of rank 1) fragment of LTL to synthesize a reactive hierarchical finite state machine that can be directly executed in FlexBE. The presented work expands on previous ROS 1 tools, and extends them to ROS 2 in a way that supports more general specifications that incorporate environmental states. This paper presents an accessible open-source demonstration that serves as a general introduction to these powerful synthesis techniques.
In autonomous driving, accurately interpreting the movements of other road users and leveraging this knowledge to forecast future trajectories is crucial. This is typically achieved through the integration of map data...
详细信息
暂无评论