REVIEW 21 cited by
Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In this study, we are interested in imbuing robots with the capability of physically-grounded task planning. Recent advancements have shown that large language models (LLMs) possess extensive knowledge useful in robotic tasks, especially in reasoning and planning. However, LLMs are constrained by their lack of world grounding and dependence on external affordance models to perceive environmental information, which cannot jointly reason with LLMs. We argue that a task planner should be an inherently grounded, unified multimodal system. To this end, we introduce Robotic Vision-Language Planning (ViLa), a novel approach for long-horizon robotic planning that leverages vision-language models (VLMs) to generate a sequence of actionable steps. ViLa directly integrates perceptual data into its reasoning and planning process, enabling a profound understanding of commonsense knowledge in the visual world, including spatial layouts and object attributes. It also supports flexible multimodal goal specification and naturally incorporates visual feedback. Our extensive evaluation, conducted in both real-robot and simulated environments, demonstrates ViLa's superiority over existing LLM-based planners, highlighting its effectiveness in a wide array of open-world manipulation tasks.
Forward citations
Cited by 21 Pith papers
-
RFTF: Reinforcement Fine-tuning for Embodied Agents with Temporal Feedback
RFTF trains a value model on temporal state orderings to supply dense rewards for reinforcement fine-tuning of vision-language-action models, achieving an average success length of 4.296 on CALVIN ABC-D with the Seer-...
-
World Action Planner: Generalizable Decision-Making with Action-Conditioned World Models
Pairing VLM-generated action proposals with rollouts from a pose-image-conditioned video world model yields high success rates in novel simulated manipulation tasks without end-to-end policy retraining.
-
RoboInter1.5: A Holistic Intermediate Representation Suite for Embodied World Modeling and Robotic Manipulation
Dense per-frame intermediate representations (traces, masks, grasp poses, subtasks) improve embodied VQA, VLA action generation, and world-model video prediction in the new 230k-episode RoboInter-Data suite.
-
ProcAgent: An Agentic Framework for Procedural Task Guidance on Edge with Human-in-the-Loop
ProcAgent demonstrates a complete step-by-step assembly assistant that runs on a single edge device by pairing cheap continuous perception with on-demand vision-language verification, a task graph, and human confirmation.
-
Visual-Language-Guided Task Planning for Horticultural Robots
A vision-language model drives a simulated greenhouse robot through simple crop-inspection tasks with ~87% success, but long multi-target tasks collapse to under 10% success.
-
SkillWrapper: Generative Predicate Invention for Task-level Robot Planning
SkillWrapper learns human-readable skill models from images via VLM predicate invention, but its provable soundness/completeness claim is not established.
-
Robix: A Unified Model for Robot Interaction, Reasoning and Planning
A three-stage-trained VLM unifies robot planning and dialogue, and beats commercial VLMs on the authors' interactive-task benchmarks.
-
T-Rex: Task-Adaptive Spatial Representation Extraction for Robotic Manipulation with Vision-Language Models
A zero-training framework that adaptively selects spatial representation extractors per object and per task stage improves real-world robot manipulation success and efficiency over fixed-representation baselines.
-
Gondola: Grounded Vision Language Planning for Generalizable Robotic Manipulation
Gondola generates multi-view segmentation-mask-grounded next-step plans for robotic manipulation and reports improved generalization on the GemBench benchmark over a prior LLM-based planner.
-
GENMANIP: LLM-driven Simulation for Generalizable Instruction-Following Manipulation
GenManip is a benchmark and simulation platform with LLM-generated scene graphs for testing how robot policies generalize to new instructions, layouts, and objects.
-
UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation
UAD distills affordance knowledge from vision-language models and DINOv2 features into a lightweight task-conditioned model that predicts pixel-level manipulation regions and improves few-shot imitation learning gener...
-
Prime the search: Using large language models for guiding geometric task and motion planning by warm-starting tree search
STaLM warm-starts a hybrid-action Monte Carlo tree search with task plans generated by a single LLM query, outperforming pure search and prior LLM planners on six geometric task and motion planning problems.
-
SwitchVLA: Execution-Aware Task Switching for Vision-Language-Action Models
SwitchVLA trains a vision-language-action policy to handle mid-execution instruction changes by conditioning on contact state and a three-way behavior mode, using only existing single-task demonstrations.
-
Reinforced Reasoning for Embodied Planning
An SFT-plus-GRPO recipe lifts a 7B VLM to 35.6 percent success on EB-ALFRED versus 22.0 for GPT-4o-mini and 33.7 for Qwen2.5-VL-72B, with smaller but consistent gains on unseen EB-Habitat.
-
Learning Compositional Behaviors from Demonstration and Language
BLADE learns structured, planable action representations from language-annotated demonstrations and composes them with a symbolic planner, outperforming latent and LLM/VLM baselines on new manipulation tasks.
-
Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Review
Bimanual VLA coordination strategies, training recipes, and continuous action chunking transfer to unmanned aerial systems; the survey maps 183 works and lists fourteen shared research directions.
-
Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration
C-PEAL trains the active learning selector with a loss that raises entropy for wrong predictions and lowers it for correct ones, improving sample selection for CLIP-style models under prompt learning and LoRA.
-
Large Model Empowered Embodied AI: A Survey on Decision-Making and Embodied Learning
A review that categorizes large-model-empowered embodied AI into hierarchical and end-to-end decision-making, imitation and reinforcement learning, and world models.
-
LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks
A unified vision-language-action model that emits a sub-task description followed by a discrete action token outperforms modular and action-only baselines on simulated long-horizon tabletop tasks.
-
Toward Embodied AGI: A Review of Embodied AI and the Road Ahead
Embodied AI today sits between Level 1 and Level 2 on a new five-level roadmap toward all-purpose humanlike robots.
- CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity
Discussion (0). Sign in to comment.