CoFL: Continuous Flow Fields for Language-Conditioned Navigation
Existing language-conditioned navigation systems typically rely on modular pipelines or trajectory generators, but the latter use each scene--instruction annotation mainly to supervise one start-conditioned rollout. To address these limitations, we present CoFL, an end-to-end policy that maps a bird's-eye view (BEV) observation and a language instruction to a continuous flow field for navigation. CoFL reformulates navigation as workspace-conditioned field learning rather than start-conditioned trajectory prediction: it learns local motion vectors at arbitrary BEV locations, turning each scene--instruction annotation into dense spatial control supervision. Trajectories are generated from any start by numerical integration of the predicted field, enabling simple real-time rollout and closed-loop recovery. To enable large-scale training and evaluation, we build a dataset of over 500k BEV image--instruction pairs, each procedurally annotated with a flow field and a trajectory derived from semantic maps built on Matterport3D and ScanNet. Evaluating on strictly unseen scenes, CoFL significantly outperforms modular Vision-Language Model (VLM)-based planners and trajectory generation policies in both navigation precision and safety, while maintaining real-time inference. Finally, we deploy CoFL zero-shot in real-world experiments with BEV observations across multiple layouts, maintaining feasible closed-loop control and a high success rate.
Code (0)
등록된 구현이 없습니다.
Tasks
Trajectory PredictionSimilar Papers 제목 키워드 기반
CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation
Vision-Language Navigation has increasingly emphasized high-level instruction reasoning, memory, global map construction, and instruction decomposition, while the low-level action representation remains comparatively und…
Vision-Language NavigationCoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making
Generative models have emerged as a promising paradigm for offline multi-agent reinforcement learning (MARL), but existing approaches require many iterative sampling steps. Recent few-step acceleration methods either dis…
Multi-agent Reinforcement LearningDecision MakingA Scalable Deep Reinforcement Learning Model for Online Scheduling Coflows of Multi-Stage Jobs for High Performance Computing
Coflow is a recently proposed networking abstraction to help improve the communication performance of data-parallel computing jobs. In multi-stage jobs, each job consists of multiple coflows and is represented by a Direc…
Deep Reinforcement LearningGraph Neural NetworkReinforcement Learning (RL)SchedulingEcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Accelerators
Dilated and transposed convolutions are widely used in modern convolutional neural networks (CNNs). These kernels are used extensively during CNN training and inference of applications such as image segmentation and high…
Generative Adversarial NetworkImage GenerationImage SegmentationSemantic SegmentationDeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection
In industrial environments, new product categories arrive sequentially, requiring continual anomaly detection without access to past data. Normalizing Flows (NFs) provide exact density estimation but suffer from catastro…
Density EstimationAnomaly Detection