Enabling humanoid robots to perform long-horizon mobile manipulation planning in real-world environments based on embodied perception and comprehension abilities has been a longstanding challenge. With the recent rise of large language models (LLMs), there has been a notable increase in the development of LLM-based planners. These approaches either utilize human-provided textual representations of the real world or heavily depend on prompt engineering to extract such representations, lacking the capability to quantitatively understand the environment, such as determining the feasibility of manipulating objects. To address these limitations, we present the Instruction-Augmented Long-Horizon Planning (IALP) system, a novel framework that employs LLMs to generate feasible and optimal actions based on real-time sensor feedback, including grounded knowledge of the environment, in a closed-loop interaction. Distinct from prior works, our approach augments user instructions into PDDL problems by leveraging both the abstract reasoning capabilities of LLMs and grounding mechanisms. By conducting various real-world long-horizon tasks, each consisting of seven distinct manipulatory skills, our results demonstrate that the IALP system can efficiently solve these tasks with an average success rate exceeding 80%. Our proposed method can operate as a high-level planner, equipping robots with substantial autonomy in unstructured environments through the utilization of multi-modal sensor inputs.

This paper presents AlignBot, a novel framework designed to optimize VLM-powered customized task planning for household robots by effectively aligning with user reminders. In domestic settings, aligning task planning with user reminders poses significant challenges due to the limited quantity, diversity, and multimodal nature of the reminders. To address these challenges, AlignBot employs a fine-tuned LLaVA-7B model, functioning as an adapter for GPT-40. This adapter model internalizes diverse forms of user reminders-such as personalized preferences, corrective guidance, and contextual assistance-into structured instruction-formatted cues that prompt GPT-40 in generating customized task plans. Additionally, AlignBot integrates a dynamic retrieval mechanism that selects task-relevant historical successes as prompts for GPT-40, further enhancing task planning accuracy. To validate the effectiveness of AlignBot, experiments are conducted in real-world household environments, which are constructed within the laboratory to replicate typical household settings. A multimodal dataset with over 1,500 entries derived from volunteer reminders is used for training and evaluation. The results demonstrate that AlignBot significantly improves customized task planning, outperforming existing LLM- and VLM-powered planners by interpreting and aligning with user reminders, achieving 86.8 % success rate compared to the vanilla GPT-40 baseline at 21.6%, reflecting a 65% improvement and over four times greater effectiveness. Supplementary materials are available at: https://yding25.com/AlignBot/

Accurately recognizing the structural regions of targeted objects is crucial for successful manipulation. In this study, we concentrate on the task of hanging crumpled garments on a rack, a common scenario in household environments. This context presents two primary challenges: (1) perceiving and grasping the structural regions of garments that exhibit severe deformations and self-occlusions; (2) adjusting the configuration of garments to fit the supporting components of the rack. To address these challenges, we propose a confidence-guided grasping strategy that actively seeks garment collars through handovers between dual robotic arms. In particular, we develop an autonomous data collection procedure in real-world settings to train the collar detection network. The exact grasping pose is determined through depth-aware contour extraction, and its success is evaluated based on a specially designed metric. Furthermore, we formulate the hanging task as one-shot imitation learning with an egocentric view. To precisely align the collar with the supporting item, we propose a two-step hanging strategy that involves coarse approaching followed by fine transformation. We perform comprehensive experiments and show that our framework notably enhances the success rate compared to existing methods.

Ultrasound-based medical examination usually requires establishing proper contact between an ultrasound probe and a human body that ensures the quality of ultrasound images. The scanning skills are quite challenging for a robot to learn primarily due to the complex coupling between the applied force profile and the resulting ultrasound image quality. While reinforcement learning appears as a powerful tool for learning complex robot skills, the deployment of these algorithms in medical robots demands special attention due to the evident safety concerns that arise from physical probe-tissue interactions. In this paper, we explicitly consider external constraints on the force magnitude when searching for the optimal policy parameters to enhance safety during ultrasound-guided robotic interventions. In particular, we study policy optimization under the framework of a constrained Markov decision process. The resulting gradient-based policy update is then subject to the involved constraints, which can be readily addressed by the primal-dual interior-point technique. In addition, upon the observation that policy update requires consecutive policies to be close to each other to have stable and robust performance with reinforcement learning algorithms, we design the learning rate of policy gradient from an imitation perspective. The performance of the proposed constraint-aware policy optimization method is validated with experiments of robotic ultrasound imaging for spinal diagnosisNote to Practitioners—This paper was motivated by the problem of safely learning the optimal interaction force strategy to facilitate robotic ultrasound imaging. Existing approaches to robotic ultrasound imaging usually empirically set a constant value for the scanning force, despite the fact the force strategy plays an important role in the quality of the ultrasound images. This paper suggests the usage of reinforcement learning to identify the optimal interaction force due to the complex acoustic coupling between the force and the ultrasound image quality. Specifically, we propose constraint-aware reinforcement learning in view of the safety-critical issues as a result of physical human-probe interaction. We then conduct a theoretical analysis of the proposed safe reinforcement learning, including monotonic improvement and policy value bound under mild assumptions. Preliminary real experiments on ultrasound imaging of the spine of a phantom for scoliosis assessment suggest that the proposed approach can safely learn the optimal scanning force without violating the prescribed force threshold. In the future, we would like to apply our approach to learning the optimal scanning force on different organs of interest of human subjects.

Fabric alignment is essential to key production processes such as cutting, sewing, and fusing in garment manufacturing. Traditionally, this task has relied heavily on the dexterity and expertise of skilled human workers. Although automated systems have been introduced, they often lack the flexibility required for complex alignment tasks. In this paper, we present a novel robotic fabric alignment framework that fully automates the process with high precision and adaptability. First, we propose a coarse-to-fine alignment strategy, where an initial imprecise target position is roughly computed based on a basic perception module and eye-to-hand calibration. This is followed by a sliding mode control (SMC)-based visual servoing approach (in an eye-in-hand configuration) to ensure a close-up view of feedback features for the fine alignment process. Additionally, we consider system disturbances estimated by a fuzzy logic system (FLS) and combine it with the controller to further enhance the system’s robustness. Finally, we developed an advanced end-effector equipped with force/torque (F/T) sensors and air-powered needle grippers for gentle fabric manipulation using admittance control. We validate our framework through a series of experiments that demonstrate its effectiveness in fabric alignment tasks.

The challenges inherent in long-horizon tasks in robotics persist due to the typical inefficient exploration and sparse rewards in traditional reinforcement learning approaches. To address these challenges, we have developed a novel algorithm, termed hlexplicit-implicit subgoal planning (EISP), designed to tackle long-horizon tasks through a divide-and-conquer approach. We utilize two primary criteria, feasibility and optimality, to ensure the quality of the generated subgoals. EISP consists of three components: a hybrid subgoal generator, a hindsight sampler, and a value selector. The hybrid subgoal generator uses an explicit model to infer subgoals and an implicit model to predict the final goal, inspired by way of human thinking that infers subgoals by using the current state and final goal as well as reason about the final goal conditioned on the current state and given subgoals. Additionally, the hindsight sampler selects valid subgoals from an offline dataset to enhance the feasibility of the generated subgoals. While the value selector utilizes the value function in reinforcement learning to filter the optimal subgoals from subgoal candidates. To validate our method, we conduct four long-horizon tasks in both simulation and the real world. The obtained quantitative and qualitative data indicate that our approach achieves promising performance compared to other baseline methods. These experimental results can be seen on the website https://sites.google.com/view/vaesi.

Garment folding is a ubiquitous domestic task that is difficult to automate due to the highly deformable nature of fabrics. In this article, we propose a novel method of learning from demonstrations that enables robots to autonomously manipulate an assistive tool to fold garments. In contrast to traditional methods (that rely on low-level pixel features), our proposed solution uses a dense visual descriptor to encode the demonstration into a high-levelhand-object graph(HoG) that allows to efficiently represent the interactions between the manipulated tool and robots. With that, we leverage graph neural network to autonomously learn the forward dynamics model from HoGs, then, given only a single demonstration, the imitation policy is optimized with a model predictive controller to accomplish the folding task. To validate the proposed approach, we conducted a detailed experimental study on a robotic platform instrumented with vision sensors and a custom-made end-effector that interacts with the folding board.

This article presents the development of a multisensor user interface to facilitate the instruction of arc welding tasks. Traditional methods to acquire hand-eye coordination skills are typically conducted through one-to-one instruction, where trainees must wear protective helmets and conduct several tests. These approaches are inefficient as the harmful light emitted from the electric arc impedes the close monitoring of the process. Practitioners can only observe a small bright spot. To tackle these problems, recent training approaches have leveraged virtual reality to safely simulate the process and visualize the geometry of the workpieces. However, the synthetic nature of these types of simulation platforms reduces their effectiveness as they fail to comprise actual welding interactions with the environment, which hinders the trainees' learning process. To provide users with a real welding experience, we have developed a new multisensor extended reality platform for arc welding training. Our system is composed of: 1) An HDR camera, monitoring the real welding spot in real time. 2) A depth sensor, capturing the 3-D geometry of the scene; and 3) A head-mounted VR display, visualizing the process safely. Our innovative platform provides users with a “bot trainer,” virtual cues of the seam geometry, automatic spot tracking, and performance scores. To validate the platform's feasibility, we conduct extensive experiments with several welding training tasks. We show that compared with the traditional training practice and recent virtual reality approaches, our automated multisensor method achieves better performances in terms of accuracy, learning curve, and effectiveness.

The communication data are becoming increasingly important for criminal network analysis nowadays, and these data provide a digital trace which can be regarded as a hidden clue to support the crack of criminal cases. Additionally, performing a timely and effective analysis on it can predict criminal intents and take efficient actions to restrain and prevent crimes. The primary work of our research is to suggest an analytical process with interactive strategies as a solution to the problem of characterizing criminal groups constructed from the communication data. It is expected to assist law enforcement agencies in the task of discovering the potential suspects and exploring the underlying structures of criminal network hidden behind the communication data. This process allows for network analysis with commonly used metrics to identify the core members. It permits exploration and visualization of the network in the goal of improving the comprehension of interesting microstructures. Most importantly, it also allows to extract community structures in an appropriate level with the label supervision strategy. Our work concludes illustrating the application of our interactive strategies to a real-world criminal investigation with mobile call logs.

Graph database is recently being adopted by data analytic systems as an appealing alternative to relational database for the management of large-scale inherent graph-like data.A great challenge of leveraging graph database technologies is to model a problem domain into graph.However, in the absence of considering application requirements or goals, current graph data modeling approaches seem to be invalid.This paper presents an exploration of a systematic approach for graph data modeling-SuMo.Starting from real world scenarios, requirements are transformed into a domain model, which acts as an intermediate model in SuMo, captures modeling features of that domain.SuMo defines a set of rules for the subsequent transformation of this domain model to produce a graph model.We applied SuMo to the modeling of a data-intensive analytic system using real datasets as an illustrating example to clarify our main idea.SuMo is empirically evaluated in terms of query performance, the experimental results indicate promising feasibility and efficiency.The major contribution of our work is a preliminary graph data modeling approach based on scenarios.

The communication data are becoming increasingly important for criminal network analysis nowadays, this data provides a digital trace which can be regarded as a hidden clue to support the crack of criminal cases.Additionally, performing a timely and effective analysis on it can predict criminal intents and take efficient actions to restrain and prevent crimes.The primary work of our research is to suggest an analytical process with interactive strategies as a solution to the problem of characterizing criminal groups constructed from the communication data.It is expected to assist law enforcement agencies in the task of discovering the potential suspects and exploring the underlying structures of criminal network hidden behind the communication data.This process allows for network analysis with commonly used metrics to identify the core members.It permits exploration and visualization of the network in the goal of improving the comprehension of interesting microstructures.Most importantly, it also allows to extract community structures in a appropriate level with the label supervision strategy.Our work concludes illustrating the application of our interactive strategies to a real world criminal investigation with mobile call logs.