OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data

This work presents OVIR-3D, a straightforward yet effective method for open-vocabulary 3D object instance retrieval without using any 3D data for training. Given a language query, the proposed method is able to return a ranked set of 3D object instance segments based on the feature similarity of the instance and the text query. This is achieved by a multi-view fusion of text-aligned 2D region proposals into 3D space, where the 2D region proposal network could leverage 2D datasets, which are more accessible and typically larger than 3D datasets. The proposed fusion process is efficient as it can be performed in real-time for most indoor 3D scenes and does not require additional training in 3D space. Experiments on public datasets and a real robot show the effectiveness of the method and its potential for applications in robot navigation and manipulation.

Context-Aware Entity Grounding with Open-Vocabulary 3D Scene Graphs

We present an Open-Vocabulary 3D Scene Graph (OVSG), a formal framework for grounding a variety of entities, such as object instances, agents, and regions, with free-form text-based queries. Unlike conventional semantic-based object localization approaches, our system facilitates context-aware entity localization, allowing for queries such as ``pick up a cup on a kitchen table" or ``navigate to a sofa on which someone is sitting". In contrast to existing research on 3D scene graphs, OVSG supports free-form text input and open-vocabulary querying. Through a series of comparative experiments using the ScanNet dataset and a self-collected dataset, we demonstrate that our proposed approach significantly surpasses the performance of previous semantic-based localization techniques. Moreover, we highlight the practical application of OVSG in real-world robot navigation and manipulation experiments.

LGMCTS: Language-Guided Monte-Carlo Tree Search for Executable Semantic Object Rearrangement

We introduce a novel approach to the executable semantic object rearrangement problem. In this challenge, a robot seeks to create an actionable plan that rearranges objects within a scene according to a pattern dictated by a natural language description. Unlike existing methods such as StructFormer and StructDiffusion, which tackle the issue in two steps by first generating poses and then leveraging a task planner for action plan formulation, our method concurrently addresses pose generation and action planning. We achieve this integration using a Language-Guided Monte-Carlo Tree Search (LGMCTS). Quantitative evaluations are provided on two simulation datasets, and complemented by qualitative tests with a real robot.

Mono-STAR: Mono-camera Scene-level Tracking and Reconstruction

We present Mono-STAR, the first real-time 3D reconstruction system that simultaneously supports semantic fusion, fast motion tracking, non-rigid object deformation, and topological change under a unified framework. The proposed system solves a new optimization problem incorporating optical-flow-based 2D constraints to deal with fast motion and a novel semantic-aware deformation graph (SAD-graph) for handling topology change. We test the proposed system under various challenging scenes and demonstrate that it significantly outperforms existing state-of-the-art methods.

Scene-level Tracking and Reconstruction without Object Priors

We present the first real-time system capable of tracking and reconstructing, individually, every visible object in a given scene, without any form of prior on the rigidness of the objects, texture existence, or object category. In contrast with previous methods such as Co-Fusion and MaskFusion that first segment the scene into individual objects and then process each object independently, the proposed method dynamically segments the non-rigid scene as part of the tracking and reconstruction process. When new measurements indicate topology change, reconstructed models are updated in real-time to reflect that change. Our proposed system can provide the live geometry and deformation of all visible objects in a novel scene in real-time, which makes it possible to be integrated seamlessly into numerous existing robotics applications that rely on object models for grasping and manipulation. The capabilities of the proposed system are demonstrated in challenging scenes that contain multiple rigid and non-rigid objects.

Cascade Attribute Network: Decomposing Reinforcement Learning Control Policies using Hierarchical Neural Networks

Reinforcement learning methods have been developed to achieve great success in training control policies in various automation tasks. However, a main challenge of the wider application of reinforcement learning in practical automation is that the training process is hard and the pretrained policy networks are hardly reusable in other similar cases. To address this problem, we propose the cascade attribute network (CAN), which utilizes its hierarchical structure to decompose a complicated control policy in terms of the requirement constraints, which we call attributes, encoded in the control tasks. We validated the effectiveness of our proposed method on two robot control scenarios with various add-on attributes. For some control tasks with more than one add-on attribute attribute, by directly assembling the attribute modules in cascade, the CAN can provide ideal control policies in a zero-shot manner.

GeoFusion: Geometric Consistency informed Scene Estimation in Dense Clutter

We propose GeoFusion, a SLAM-based scene estimation method for building an object-level semantic map in dense clutter. In dense clutter, objects are often in close contact and severe occlusions, which brings more false detections and noisy pose estimates from existing perception methods. To solve these problems, our key insight is to consider geometric consistency at the object level within a general SLAM framework. The geometric consistency is defined in two parts: geometric consistency score and geometric relation. The geometric consistency score describes the compatibility between object geometry model and observation point cloud. Meanwhile it provides a reliable measure to filter out false positives in data association. The geometric relation represents the relationship (e.g. contact) between geometric features (e.g. planes) among objects. The geometric relation makes the graph optimization for poses more robust and accurate. GeoFusion can robustly and efficiently infer the object labels, 6D object poses and spatial relations from continutous noisy semantic measurements. We quantitatively evaluate our method using observations from a Fetch mobile manipulation robot. Our results demonstrate greater robustness against false estimates than frame-by-frame pose estimation from the state-of-the-art convolutional neural network.

GlassLoc: Plenoptic Grasp Pose Detection in Transparent Clutter

Transparent objects are prevalent across many environments of interest for dexterous robotic manipulation. Such transparent material leads to considerable uncertainty for robot perception and manipulation, and remains an open challenge for robotics. This problem is exacerbated when multiple transparent objects cluster into piles of clutter. In household environments, for example, it is common to encounter piles of glassware in kitchens, dining rooms, and reception areas, which are essentially invisible to modern robots. We present the GlassLoc algorithm for grasp pose detection of transparent objects in transparent clutter using plenoptic sensing. GlassLoc classifies graspable locations in space informed by a Depth Likelihood Volume (DLV) descriptor. We extend the DLV to infer the occupancy of transparent objects over a given space from multiple plenoptic viewpoints. We demonstrate and evaluate the GlassLoc algorithm on a Michigan Progress Fetch mounted with a first-generation Lytro. The effectiveness of our algorithm is evaluated through experiments for grasp detection and execution with a variety of transparent glassware in minor clutter.

Cascade Attribute Learning Network

We propose the cascade attribute learning network (CALNet), which can learn attributes in a control task separately and assemble them together. Our contribution is twofold: first we propose attribute learning in reinforcement learning (RL). Attributes used to be modeled using constraint functions or terms in the objective function, making it hard to transfer. Attribute learning, on the other hand, models these task properties as modules in the policy network. We also propose using novel cascading compensative networks in the CALNet to learn and assemble attributes. Using the CALNet, one can zero shoot an unseen task by separately learning all its attributes, and assembling the attribute modules. We have validated the capacity of our model on a wide variety of control problems with attributes in time, position, velocity and acceleration phases.