相关论文: ESCAPE: Episodic Spatial Memory and Adaptive Execu…

Embodied task planning requires agents to execute long-horizon, goal-directed actions in complex 3D environments, where success depends on both immediate perception and accumulated experience across tasks. However, most existing LLM-based…

Data-driven methods are emerging as efficient alternatives to traditional numerical forecasting, offering fast inference and lower computational cost. Yet, for complex systems, long-term accuracy often deteriorates due to error…

Episodic memory is a psychology term which refers to the ability to recall specific events from the past. We suggest one advantage of this particular type of memory is the ability to easily assign credit to a specific state when remembered…

Accurate and efficient modeling of agent interactions is essential for trajectory generation, the core of autonomous driving systems. Existing methods, scene-centric, agent-centric, and query-centric frameworks, each present distinct…

State-of-the-art navigation methods leverage a spatial memory to generalize to new environments, but their occupancy maps are limited to capturing the geometric structures directly observed by the agent. We propose occupancy anticipation,…

Optimizing and refining action execution through exploration and interaction is a promising way for robotic manipulation. However, practical approaches to interaction-driven robotic learning are still underexplored, particularly for…

Cognitive maps play a crucial role in facilitating flexible behaviour by representing spatial and conceptual relationships within an environment. The ability to learn and infer the underlying structure of the environment is crucial for…

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…

In order to solve complex, long-horizon tasks, intelligent robots need to carry out high-level, abstract planning and reasoning in conjunction with motion planning. However, abstract models are typically lossy and plans or policies computed…

While modern policy optimization methods can do complex manipulation from sensory data, they struggle on problems with extended time horizons and multiple sub-goals. On the other hand, task and motion planning (TAMP) methods scale to long…

Diffusion policies have emerged as a powerful framework for robotic visuomotor control, yet they often lack the robustness to recover from subtask failures in long-horizon, multi-stage tasks and their learned representations of observations…

Optimisation-based algorithms known as Moving Horizon Estimator (MHE) have been developed through the years. This paper illustrates the implementation of the policy introduced in the companion paper submitted to the 18th IFAC Workshop on…

In indoor environments, multi-robot visual (RGB-D) mapping and exploration hold immense potential for application in domains such as domestic service and logistics, where deploying multiple robots in the same environment can significantly…

We present 3D-Anchored Lookahead Planning (3D-ALP), a System 2 reasoning engine for robotic manipulation that combines Monte Carlo Tree Search (MCTS) with a 3D-consistent world model as the rollout oracle. Unlike reactive policies that…

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…

Current interactive LLM agents rely on goal-conditioned stepwise planning, where environmental understanding is acquired reactively during execution rather than established beforehand. This temporal inversion leads to Delayed Environmental…

Current robotic planning methods often rely on predicting multi-frame images with full pixel details. While this fine-grained approach can serve as a generic world model, it introduces two significant challenges for downstream policy…

Learning high-level navigation behaviors has important implications: it enables robots to build compact visual memory for repeating demonstrations and to build sparse topological maps for planning in novel environments. Existing approaches…

Constructing compact and informative 3D scene representations is essential for effective embodied exploration and reasoning, especially in complex environments over extended periods. Existing representations, such as object-centric 3D scene…

Embodied AI agents responsible for executing interconnected, long-sequence household tasks often face difficulties with in-context memory, leading to inefficiencies and errors in task execution. To address this issue, we introduce KARMA, an…