CU-Multi: A Dataset for Multi-Robot Data Association

Multi-robot systems (MRSs) are valuable for tasks such as search and rescue due to their ability to coordinate over shared observations. A central challenge in these systems is aligning independently collected perception data across space and time, i.e., multi-robot data association. While recent advances in collaborative SLAM (C-SLAM), map merging, and inter-robot loop closure detection have significantly progressed the field, evaluation strategies still predominantly rely on splitting a single trajectory from single-robot SLAM datasets into multiple segments to simulate multiple robots. Without careful consideration to how a single trajectory is split, this approach will fail to capture realistic pose-dependent variation in observations of a scene inherent to multi-robot systems. To address this gap, we present CU-Multi, a multi-robot dataset collected over multiple days at two locations on the University of Colorado Boulder campus. Using a single robotic platform, we generate four synchronized runs with aligned start times and deliberate percentages of trajectory overlap. CU-Multi includes RGB-D, GPS with accurate geospatial heading, and semantically annotated LiDAR data. By introducing controlled variations in trajectory overlap and dense lidar annotations, CU-Multi offers a compelling alternative for evaluating methods in multi-robot data association. Instructions on accessing the dataset, support code, and the latest updates are publicly available at https://arpg.github.io/cumulti

Spatial-LLaVA: Enhancing Large Language Models with Spatial Referring Expressions for Visual Understanding

Multimodal large language models (MLLMs) have demonstrated remarkable abilities in comprehending visual input alongside text input. Typically, these models are trained on extensive data sourced from the internet, which are sufficient for general tasks such as scene understanding and question answering. However, they often underperform on specialized tasks where online data is scarce, such as determining spatial relationships between objects or localizing unique target objects within a group of objects sharing similar features. In response to this challenge, we introduce the SUN-Spot v2.0 dataset1, now comprising a total of 90k image-caption pairs and additional annotations on the landmark objects. Each image-caption pair utilizes Set-of-Marks prompting as an additional indicator, mapping each landmark object in the image to the corresponding object mentioned in the caption. Furthermore, we present Spatial-LLaVA, an MLLM trained on conversational data generated by a state-of-the-art language model using the SUNSpot v2.0 dataset. Our approach ensures a robust alignment between the objects in the images and their corresponding object mentions in the captions, enabling our model to learn spatial referring expressions without bias from the semantic information of the objects. Spatial-LLaVA outperforms previous methods by 3.15% on the zero-shot Visual Spatial Reasoning benchmark dataset. Spatial-LLaVA is specifically designed to precisely understand spatial referring expressions, making it highly applicable for tasks in real-world scenarios such as autonomous navigation and interactive robotics, where precise object recognition is critical.

Tell Me Where to Go: A Composable Framework for Context-Aware Embodied Robot Navigation

Humans have the remarkable ability to navigate through unfamiliar environments by solely relying on our prior knowledge and descriptions of the environment. For robots to perform the same type of navigation, they need to be able to associate natural language descriptions with their associated physical environment with a limited amount of prior knowledge. Recently, Large Language Models (LLMs) have been able to reason over billions of parameters and utilize them in multi-modal chat-based natural language responses. However, LLMs lack real-world awareness and their outputs are not always predictable. In this work, we develop NavCon, a low-bandwidth framework that solves this lack of real-world generalization by creating an intermediate layer between an LLM and a robot navigation framework in the form of Python code. Our intermediate shoehorns the vast prior knowledge inherent in an LLM model into a series of input and output API instructions that a mobile robot can understand. We evaluate our method across four different environments and command classes on a mobile robot and highlight our NavCon's ability to interpret contextual commands.