相关论文: ESCAPE: Episodic Spatial Memory and Adaptive Execu…
Humans can perform complex tasks with long-term objectives by planning, reasoning, and forecasting outcomes of actions. For embodied agents to achieve similar capabilities, they must gain knowledge of the environment transferable to novel…
Formulating expert policies as macro actions promises to alleviate the long-horizon issue via structured exploration and efficient credit assignment. However, traditional option-based multi-policy transfer methods suffer from inefficient…
Modern computer systems need to execute under strict safety constraints (e.g., a power limit), but doing so often conflicts with their ability to deliver high performance (i.e. minimal latency). Prior work uses machine learning to…
Spatial understanding is a critical aspect of most robotic tasks, particularly when generalization is important. Despite the impressive results of deep generative models in complex manipulation tasks, the absence of a representation that…
Low-cost distributed robots suffer from limited onboard computing power, resulting in excessive computation time when navigating in cluttered environments. This paper presents Edge Accelerated Robot Navigation (EARN), to achieve real-time…
Most existing spatial reasoning benchmarks focus on static or globally observable environments, failing to capture the challenges of long-horizon reasoning and memory utilization under partial observability and dynamic changes. We introduce…
The growth of compute-intensive AI tasks highlights the need to mitigate the processing costs and improve performance and energy efficiency. This necessitates the integration of intelligent agents as architectural adaptation supervisors…
Traditional AI alignment primarily focuses on individual model outputs; however, autonomous agents in long-horizon workflows require sustained reliability across entire interaction trajectories. We introduce APEMO (Affect-aware Peak-End…
Embodied intelligence aims to enable robots to learn, reason, and generalize robustly across complex real-world environments. However, existing approaches often struggle with partial observability, fragmented spatial reasoning, and…
As Large Language Models (LLMs) evolve from text-completion tools into fully fledged agents operating in dynamic environments, they must address the challenge of continually learning and retaining long-term knowledge. Many biological…
Shape completion, a crucial task in 3D computer vision, involves predicting and filling the missing regions of scanned or partially observed objects. Current methods expect known pose or canonical coordinates and do not perform well under…
Spatial memory, or the ability to remember and recall specific locations and objects, is central to autonomous agents' ability to carry out tasks in real environments. However, most existing artificial memory modules are not very adept at…
Enabling humanoid robots to perform long-horizon mobile manipulation planning in real-world environments based on embodied perception and comprehension abilities has been a longstanding challenge. With the recent rise of large language…
Vision-centric hierarchical embodied models have demonstrated strong potential. However, existing methods lack spatial awareness capabilities, limiting their effectiveness in bridging visual plans to actionable control in complex…
Mixture-of-Experts (MoE) models are designed to enhance the efficiency of large language models (LLMs) without proportionally increasing the computational demands. However, their deployment on edge devices still faces significant challenges…
This document is one of the deliverable reports created for the ESCAPE project. ESCAPE stands for Energy-efficient Scalable Algorithms for Weather Prediction at Exascale. The project develops world-class, extreme-scale computing…
The remote embodied referring expression (REVERIE) task requires an agent to navigate through complex indoor environments and localize a remote object specified by high-level instructions, such as "bring me a spoon", without…
Neural-based motion planning methods have achieved remarkable progress for robotic manipulators, yet a fundamental challenge lies in simultaneously accounting for both the robot's physical shape and the surrounding environment when…
The paper proposes a reliable and robust planning solution to the long range robotic navigation problem in extremely cluttered environments. A two-layer planning architecture is proposed that leverages both the environment map and the…
Many robotic applications require the agent to perform long-horizon tasks in partially observable environments. In such applications, decision making at any step can depend on observations received far in the past. Hence, being able to…