Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?
While recent video world models can generate highly realistic videos, their ability to perform semantic reasoning and planning remains unclear and unquantified. We introduce Target-Bench, the first benchmark that enables comprehensive evaluation of video world models' semantic reasoning, spatial estimation, and planning capabilities. Target-Bench provides 450 robot-collected scenarios spanning 47 semantic categories, with SLAM-based trajectories serving as motion tendency references. Our benchmark reconstructs motion from generated videos with a metric scale recovery mechanism, enabling the evaluation of planning performance with five complementary metrics that focus on target-approaching capability and directional consistency. Our evaluation result shows that the best off-the-shelf model achieves only a 0.341 overall score, revealing a significant gap between realistic visual generation and semantic reasoning in current video world models. Furthermore, we demonstrate that fine-tuning process on a relatively small real-world robot dataset can significantly improve task-level planning performance.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance
We introduce CREStE, a scalable learning-based mapless navigation framework to address the open-world generalization and robustness challenges of outdoor urban navigation. Key to achieving this is learning perceptual rep…
Active LearningcounterfactualNavigateSem-NaVAE: Semantically-Guided Outdoor Mapless Navigation via Generative Trajectory Priors
This work presents a mapless navigation approach for outdoor applications. It combines the exploratory capacity of conditional variational autoencoders (CVAEs) to generate trajectories and the semantic segmentation capab…
Semantic SegmentationVirtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation
We present a learning-based mapless motion planner by taking the sparse 10-dimensional range findings and the target position with respect to the mobile robot coordinate frame as input and the continuous steering command…
continuous-controlContinuous ControlDeep Reinforcement LearningNavigate+3Curiosity-driven Exploration for Mapless Navigation with Deep Reinforcement Learning
This paper investigates exploration strategies of Deep Reinforcement Learning (DRL) methods to learn navigation policies for mobile robots. In particular, we augment the normal external reward for training DRL algorithms…
Deep Reinforcement LearningNavigatereinforcement-learningReinforcement Learning+1SignScene: Visual Sign Grounding for Mapless Navigation
Navigational signs enable humans to navigate unfamiliar environments without maps. This work studies how robots can similarly exploit signs for mapless navigation in the open world. A central challenge lies in interpreti…