This paper introduces a robot active task cognition framework for Situation-Aware Task Planning (SATP), leveraging visual scene understanding to generate action sequences. By integrating object knowledge, user preferences, and Large Language Models (LLMs), SATP interprets the robot’s current visual perception, and creates procedural actions that align with what the robot “sees”. Diverging from conventional methods requiring explicit verbal commands, our SATP framework autonomously performs task cognition, actively formulating robot-executable action sequences directly from visual input. Initially, a novel approach for describing the visual scene is presented, enabling the robot to grasp detailed object-level properties and inter-object relationships based on its observations. Building on this, a knowledge base for active task cognition is constructed using ontology technology. Furthermore, we develop a two-stage dual-feedback task planner, ReProg+, powered by LLMs, specifically designed for situation-aware task planning grounded in visual data. The efficacy, reliability, and advantages of our solution are thoroughly validated in real-world visual scenarios. Additionally, SATP has been tested with a real robot, with results confirming the feasibility and effectiveness of our approach.

Service robots operating in unstructured environments must effectively recognize and segment unknown objects to enhance their functionality. Traditional supervised learning-based segmentation techniques require extensive annotated datasets, which are impractical for the diversity of objects encountered in real-world scenarios. Unseen object instance segmentation (UOIS) methods aim to address this by training models on synthetic data to generalize to novel objects, but they often suffer from the simulation-to-reality gap. This article proposes a novel approach (ZISVFM) for solving UOIS by leveraging the powerful zero-shot capability of the segment anything model (SAM) and explicit visual representations from a self-supervised vision transformer (ViT). The proposed framework operates in the following three stages: generating object-agnostic mask proposals from colorized depth images using SAM, refining these proposals using attention-based features from the self-supervised ViT to filter nonobject masks, and applying K-Medoids clustering to generate point prompts that guide SAM toward precise object segmentation. Experimental validation on two benchmark datasets and a self-collected dataset demonstrates the superior performance of ZISVFM in complex environments, including hierarchical settings such as cabinets, drawers, and handheld objects.