Learning from Feedback: Semantic Enhancement for Object SLAM Using Foundation Models

Semantic Simultaneous Localization and Mapping (SLAM) systems struggle to map semantically similar objects in close proximity, especially in cluttered indoor environments. We introduce Semantic Enhancement for Object SLAM (SEO-SLAM), a novel SLAM system that leverages Vision-Language Models (VLMs) and Multimodal Large Language Models (MLLMs) to enhance object-level semantic mapping in such environments. SEO-SLAM tackles existing challenges by (1) generating more specific and descriptive open-vocabulary object labels using MLLMs, (2) simultaneously correcting factors causing erroneous landmarks, and (3) dynamically updating a multiclass confusion matrix to mitigate object detector biases. Our approach enables more precise distinctions between similar objects and maintains map coherence by reflecting scene changes through MLLM feedback. We evaluate SEO-SLAM on our challenging dataset, demonstrating enhanced accuracy and robustness in environments with multiple similar objects. Our system outperforms existing approaches in terms of landmark matching accuracy and semantic consistency. Results show the feedback from MLLM improves object-centric semantic mapping. Our dataset is publicly available at: jungseokhong.com/SEO-SLAM.

Opti-Acoustic Semantic SLAM with Unknown Objects in Underwater Environments

Despite recent advances in semantic Simultaneous Localization and Mapping (SLAM) for terrestrial and aerial applications, underwater semantic SLAM remains an open and largely unaddressed research problem due to the unique sensing modalities and the object classes found underwater. This paper presents an object-based semantic SLAM method for underwater environments that can identify, localize, classify, and map a wide variety of marine objects without a priori knowledge of the object classes present in the scene. The method performs unsupervised object segmentation and object-level feature aggregation, and then uses opti-acoustic sensor fusion for object localization. Probabilistic data association is used to determine observation to landmark correspondences. Given such correspondences, the method then jointly optimizes landmark and vehicle position estimates. Indoor and outdoor underwater datasets with a wide variety of objects and challenging acoustic and lighting conditions are collected for evaluation and made publicly available. Quantitative and qualitative results show the proposed method achieves reduced trajectory error compared to baseline methods, and is able to obtain comparable map accuracy to a baseline closed-set method that requires hand-labeled data of all objects in the scene.

Diver Identification Using Anthropometric Data Ratios for Underwater Multi-Human-Robot Collaboration

Recent advances in efficient design, perception algorithms, and computing hardware have made it possible to create improved human-robot interaction (HRI) capabilities for autonomous underwater vehicles (AUVs). To conduct secure missions as underwater human-robot teams, AUVs require the ability to accurately identify divers. However, this remains an open problem due to divers' challenging visual features, mainly caused by similar-looking scuba gear. In this paper, we present a novel algorithm that can perform diver identification using either pre-trained models or models trained during deployment. We exploit anthropometric data obtained from diver pose estimates to generate robust features that are invariant to changes in distance and photometric conditions. We also propose an embedding network that maximizes inter-class distances in the feature space and minimizes those for the intra-class features, which significantly improves classification performance. Furthermore, we present an end-to-end diver identification framework that operates on an AUV and evaluate the accuracy of the proposed algorithm. Quantitative results in controlled-water experiments show that our algorithm achieves a high level of accuracy in diver identification.

Self-supervised Wide Baseline Visual Servoing via 3D Equivariance

One of the challenging input settings for visual servoing is when the initial and goal camera views are far apart. Such settings are difficult because the wide baseline can cause drastic changes in object appearance and cause occlusions. This paper presents a novel self-supervised visual servoing method for wide baseline images which does not require 3D ground truth supervision. Existing approaches that regress absolute camera pose with respect to an object require 3D ground truth data of the object in the forms of 3D bounding boxes or meshes. We learn a coherent visual representation by leveraging a geometric property called 3D equivariance-the representation is transformed in a predictable way as a function of 3D transformation. To ensure that the feature-space is faithful to the underlying geodesic space, a geodesic preserving constraint is applied in conjunction with the equivariance. We design a Siamese network that can effectively enforce these two geometric properties without requiring 3D supervision. With the learned model, the relative transformation can be inferred simply by following the gradient in the learned space and used as feedback for closed-loop visual servoing. Our method is evaluated on objects from the YCB dataset, showing meaningful outperformance on a visual servoing task, or object alignment task with respect to state-of-the-art approaches that use 3D supervision. Ours yields more than 35% average distance error reduction and more than 90% success rate with 3cm error tolerance.

Using Monocular Vision and Human Body Priors for AUVs to Autonomously Approach Divers

Direct communication between humans and autonomous underwater vehicles (AUVs) is a relatively underexplored area in human-robot interaction (HRI) research, although many tasks (\eg surveillance, inspection, and search-and-rescue) require close diver-robot collaboration. Many core functionalities in this domain are in need of further study to improve robotic capabilities for ease of interaction. One of these is the challenge of autonomous robots approaching and positioning themselves relative to divers to initiate and facilitate interactions. Suboptimal AUV positioning can lead to poor quality interaction and lead to excessive cognitive and physical load for divers. In this paper, we introduce a novel method for AUVs to autonomously navigate and achieve diver-relative positioning to begin interaction. Our method is based only on monocular vision, requires no global localization, and is computationally efficient. We present our algorithm along with an implementation of said algorithm on board both a simulated and physical AUV, performing extensive evaluations in the form of closed-water tests in a controlled pool. Analysis of our results show that the proposed monocular vision-based algorithm performs reliably and efficiently operating entirely on-board the AUV.

ROW-SLAM: Under-Canopy Cornfield Semantic SLAM

We study a semantic SLAM problem faced by a robot tasked with autonomous weeding under the corn canopy. The goal is to detect corn stalks and localize them in a global coordinate frame. This is a challenging setup for existing algorithms because there is very little space between the camera and the plants, and the camera motion is primarily restricted to be along the row. To overcome these challenges, we present a multi-camera system where a side camera (facing the plants) is used for detection whereas front and back cameras are used for motion estimation. Next, we show how semantic features in the environment (corn stalks, ground, and crop planes) can be used to develop a robust semantic SLAM solution and present results from field trials performed throughout the growing season across various cornfields.

Semantically-Aware Strategies for Stereo-Visual Robotic Obstacle Avoidance

Mobile robots in unstructured, mapless environments must rely on an obstacle avoidance module to navigate safely. The standard avoidance techniques estimate the locations of obstacles with respect to the robot but are unaware of the obstacles' identities. Consequently, the robot cannot take advantage of semantic information about obstacles when making decisions about how to navigate. We propose an obstacle avoidance module that combines visual instance segmentation with a depth map to classify and localize objects in the scene. The system avoids obstacles differentially, based on the identity of the objects: for example, the system is more cautious in response to unpredictable objects such as humans. The system can also navigate closer to harmless obstacles and ignore obstacles that pose no collision danger, enabling it to navigate more efficiently. We validate our approach in two simulated environments: one terrestrial and one underwater. Results indicate that our approach is feasible and can enable more efficient navigation strategies.

Visual Diver Face Recognition for Underwater Human-Robot Interaction

This paper presents a deep-learned facial recognition method for underwater robots to identify scuba divers. Specifically, the proposed method is able to recognize divers underwater with faces heavily obscured by scuba masks and breathing apparatus. Our contribution in this research is towards robust facial identification of individuals under significant occlusion of facial features and image degradation from underwater optical distortions. With the ability to correctly recognize divers, autonomous underwater vehicles (AUV) will be able to engage in collaborative tasks with the correct person in human-robot teams and ensure that instructions are accepted from only those authorized to command the robots. We demonstrate that our proposed framework is able to learn discriminative features from real-world diver faces through different data augmentation and generation techniques. Experimental evaluations show that this framework achieves a 3-fold increase in prediction accuracy compared to the state-of-the-art (SOTA) algorithms and is well-suited for embedded inference on robotic platforms.

TrashCan: A Semantically-Segmented Dataset towards Visual Detection of Marine Debris

This paper presents TrashCan, a large dataset comprised of images of underwater trash collected from a variety of sources, annotated both using bounding boxes and segmentation labels, for development of robust detectors of marine debris. The dataset has two versions, TrashCan-Material and TrashCan-Instance, corresponding to different object class configurations. The eventual goal is to develop efficient and accurate trash detection methods suitable for onboard robot deployment. Along with information about the construction and sourcing of the TrashCan dataset, we present initial results of instance segmentation from Mask R-CNN and object detection from Faster R-CNN. These do not represent the best possible detection results but provides an initial baseline for future work in instance segmentation and object detection on the TrashCan dataset.

Design and Experiments with LoCO AUV: A Low Cost Open-Source Autonomous Underwater Vehicle

In this paper we present LoCO AUV, a Low-Cost, Open Autonomous Underwater Vehicle. LoCO is a general-purpose, single-person-deployable, vision-guided AUV, rated to a depth of 100 meters. We discuss the open and expandable design of this underwater robot, as well as the design of a simulator in Gazebo. Additionally, we explore the platform's preliminary local motion control and state estimation abilities, which enable it to perform maneuvers autonomously. In order to demonstrate its usefulness for a variety of tasks, we implement a variety of our previously presented human-robot interaction capabilities on LoCO, including gestural control, diver following, and robot communication via motion. Finally, we discuss the practical concerns of deployment and our experiences in using this robot in pools, lakes, and the ocean. All design details, instructions on assembly, and code will be released under a permissive, open-source license.