Interactive Navigation in Environments with Traversable Obstacles Using Large Language and Vision-Language Models
This work addresses interactive navigation for robots in environments with traversable obstacles, offering a novel framework that leverages pre-trained models for fast deployment, though it is incremental in applying existing models to a specific domain.
The paper tackles the problem of enabling robots to navigate through traversable obstacles like curtains and grass by using large language and vision-language models to create an action-aware costmap for path planning, achieving effective navigation without fine-tuning or additional annotated data.
This paper proposes an interactive navigation framework by using large language and vision-language models, allowing robots to navigate in environments with traversable obstacles. We utilize the large language model (GPT-3.5) and the open-set Vision-language Model (Grounding DINO) to create an action-aware costmap to perform effective path planning without fine-tuning. With the large models, we can achieve an end-to-end system from textual instructions like "Can you pass through the curtains to deliver medicines to me?", to bounding boxes (e.g., curtains) with action-aware attributes. They can be used to segment LiDAR point clouds into two parts: traversable and untraversable parts, and then an action-aware costmap is constructed for generating a feasible path. The pre-trained large models have great generalization ability and do not require additional annotated data for training, allowing fast deployment in the interactive navigation tasks. We choose to use multiple traversable objects such as curtains and grasses for verification by instructing the robot to traverse them. Besides, traversing curtains in a medical scenario was tested. All experimental results demonstrated the proposed framework's effectiveness and adaptability to diverse environments.