Max Q. -H. Meng

Fan Bai, Ke Yan, Xiaoyu Bai et al.

Medical image analysis using deep learning is often challenged by limited labeled data and high annotation costs. Fine-tuning the entire network in label-limited scenarios can lead to overfitting and suboptimal performance. Recently, prompt tuning has emerged as a more promising technique that introduces a few additional tunable parameters as prompts to a task-agnostic pre-trained model, and updates only these parameters using supervision from limited labeled data while keeping the pre-trained model unchanged. However, previous work has overlooked the importance of selective labeling in downstream tasks, which aims to select the most valuable downstream samples for annotation to achieve the best performance with minimum annotation cost. To address this, we propose a framework that combines selective labeling with prompt tuning (SLPT) to boost performance in limited labels. Specifically, we introduce a feature-aware prompt updater to guide prompt tuning and a TandEm Selective LAbeling (TESLA) strategy. TESLA includes unsupervised diversity selection and supervised selection using prompt-based uncertainty. In addition, we propose a diversified visual prompt tuning strategy to provide multi-prompt-based discrepant predictions for TESLA. We evaluate our method on liver tumor segmentation and achieve state-of-the-art performance, outperforming traditional fine-tuning with only 6% of tunable parameters, also achieving 94% of full-data performance by labeling only 5% of the data.

Fan Bai, Xiaohan Xing, Yutian Shen et al.

Weakly supervised methods, such as class activation maps (CAM) based, have been applied to achieve bleeding segmentation with low annotation efforts in Wireless Capsule Endoscopy (WCE) images. However, the CAM labels tend to be extremely noisy, and there is an irreparable gap between CAM labels and ground truths for medical images. This paper proposes a new Discrepancy-basEd Active Learning (DEAL) approach to bridge the gap between CAMs and ground truths with a few annotations. Specifically, to liberate labor, we design a novel discrepancy decoder model and a CAMPUS (CAM, Pseudo-label and groUnd-truth Selection) criterion to replace the noisy CAMs with accurate model predictions and a few human labels. The discrepancy decoder model is trained with a unique scheme to generate standard, coarse and fine predictions. And the CAMPUS criterion is proposed to predict the gaps between CAMs and ground truths based on model divergence and CAM divergence. We evaluate our method on the WCE dataset and results show that our method outperforms the state-of-the-art active learning methods and reaches comparable performance to those trained with full annotated datasets with only 10% of the training data labeled.

Fan Bai, Yuxin Du, Tiejun Huang et al.

Medical image analysis is essential to clinical diagnosis and treatment, which is increasingly supported by multi-modal large language models (MLLMs). However, previous research has primarily focused on 2D medical images, leaving 3D images under-explored, despite their richer spatial information. This paper aims to advance 3D medical image analysis with MLLMs. To this end, we present a large-scale 3D multi-modal medical dataset, M3D-Data, comprising 120K image-text pairs and 662K instruction-response pairs specifically tailored for various 3D medical tasks, such as image-text retrieval, report generation, visual question answering, positioning, and segmentation. Additionally, we propose M3D-LaMed, a versatile multi-modal large language model for 3D medical image analysis. Furthermore, we introduce a new 3D multi-modal medical benchmark, M3D-Bench, which facilitates automatic evaluation across eight tasks. Through comprehensive evaluation, our method proves to be a robust model for 3D medical image analysis, outperforming existing solutions. All code, data, and models are publicly available at: https://github.com/BAAI-DCAI/M3D.

Fei Meng, Zijiang Yang, Xinyu Mao et al.

Robot manipulators operating in uncertain and non-convex environments present significant challenges for safe and optimal motion planning. Existing methods often struggle to provide efficient and formally certified collision risk guarantees, particularly when dealing with complex geometries and non-Gaussian uncertainties. This article proposes a novel risk-bounded motion planning framework to address this unmet need. Our approach integrates a rigid manipulator deep stochastic Koopman operator (RM-DeSKO) model to robustly predict the robot's state distribution under motion uncertainty. We then introduce an efficient, hierarchical verification method that combines parallelizable physics simulations with sum-of-squares (SOS) programming as a filter for fine-grained, formal certification of collision risk. This method is embedded within a Model Predictive Path Integral (MPPI) controller that uniquely utilizes binary collision information from SOS decomposition to improve its policy. The effectiveness of the proposed framework is validated on two typical robot manipulators through extensive simulations and real-world experiments, including a challenging human-robot collaboration scenario, demonstrating sim-to-real transfer of the learned model and its ability to generate safe and efficient trajectories in complex, uncertain settings.

Jianbang Liu, Xinyu Mao, Yuqi Fang et al.

With the rapid development of machine learning, autonomous driving has become a hot issue, making urgent demands for more intelligent perception and planning systems. Self-driving cars can avoid traffic crashes with precisely predicted future trajectories of surrounding vehicles. In this work, we review and categorize existing learning-based trajectory forecasting methods from perspectives of representation, modeling, and learning. Moreover, we make our implementation of Target-driveN Trajectory Prediction publicly available at https://github.com/Henry1iu/TNT-Trajectory-Predition, demonstrating its outstanding performance whereas its original codes are withheld. Enlightenment is expected for researchers seeking to improve trajectory prediction performance based on the achievement we have made.

Keyu Li, Yangxin Xu, Max Q. -H. Meng

Abdominal ultrasound imaging has been widely used to assist in the diagnosis and treatment of various abdominal organs. In order to shorten the examination time and reduce the cognitive burden on the sonographers, we present a classification method that combines the deep learning techniques and k-Nearest-Neighbor (k-NN) classification to automatically recognize various abdominal organs in the ultrasound images in real time. Fine-tuned deep neural networks are used in combination with PCA dimension reduction to extract high-level features from raw ultrasound images, and a k-NN classifier is employed to predict the abdominal organ in the image. We demonstrate the effectiveness of our method in the task of ultrasound image classification to automatically recognize six abdominal organs. A comprehensive comparison of different configurations is conducted to study the influence of different feature extractors and classifiers on the classification accuracy. Both quantitative and qualitative results show that with minimal training effort, our method can "lazily" recognize the abdominal organs in the ultrasound images in real time with an accuracy of 96.67%. Our implementation code is publicly available at: https://github.com/LeeKeyu/abdominal_ultrasound_classification.

Delong Zhu, Chaoqun Wang, Wenshan Wang et al.

This paper presents a fundamental algorithm, called VDB-EDT, for Euclidean distance transform (EDT) based on the VDB data structure. The algorithm executes on grid maps and generates the corresponding distance field for recording distance information against obstacles, which forms the basis of numerous motion planning algorithms. The contributions of this work mainly lie in three folds. Firstly, we propose a novel algorithm that can facilitate distance transform procedures by optimizing the scheduling priorities of transform functions, which significantly improves the running speed of conventional EDT algorithms. Secondly, we for the first time introduce the memory-efficient VDB data structure, a customed B+ tree, to represent the distance field hierarchically. Benefiting from the special index and caching mechanism, VDB shows a fast (average \textit{O}(1)) random access speed, and thus is very suitable for the frequent neighbor-searching operations in EDT. Moreover, regarding the small scale of existing datasets, we release a large-scale dataset captured from subterranean environments to benchmark EDT algorithms. Extensive experiments on the released dataset and publicly available datasets show that VDB-EDT can reduce memory consumption by about 30%-85%, depending on the sparsity of the environment, while maintaining a competitive running speed with the fastest array-based implementation. The experiments also show that VDB-EDT can significantly outperform the state-of-the-art EDT algorithm in both runtime and memory efficiency, which strongly demonstrates the advantages of our proposed method. The released dataset and source code are available on https://github.com/zhudelong/VDB-EDT.

Jianbang Liu, Yuqi Fang, Delong Zhu et al.

Human activities are hugely restricted by COVID-19, recently. Robots that can conduct inter-floor navigation attract much public attention, since they can substitute human workers to conduct the service work. However, current robots either depend on human assistance or elevator retrofitting, and fully autonomous inter-floor navigation is still not available. As the very first step of inter-floor navigation, elevator button segmentation and recognition hold an important position. Therefore, we release the first large-scale publicly available elevator panel dataset in this work, containing 3,718 panel images with 35,100 button labels, to facilitate more powerful algorithms on autonomous elevator operation. Together with the dataset, a number of deep learning based implementations for button segmentation and recognition are also released to benchmark future methods in the community. The dataset will be available at \url{https://github.com/zhudelong/elevator_button_recognition

Yinchuan Wang, Bin Ren, Xiang Zhang et al.

LiDAR-based SLAM is recognized as one effective method to offer localization guidance in rough environments. However, off-the-shelf LiDAR-based SLAM methods suffer from significant pose estimation drifts, particularly components relevant to the vertical direction, when passing to uneven terrains. This deficiency typically leads to a conspicuously distorted global map. In this article, a LiDAR-based SLAM method is presented to improve the accuracy of pose estimations for ground vehicles in rough terrains, which is termed Rotation-Optimized LiDAR-Only (ROLO) SLAM. The method exploits a forward location prediction to coarsely eliminate the location difference of consecutive scans, thereby enabling separate and accurate determination of the location and orientation at the front-end. Furthermore, we adopt a parallel-capable spatial voxelization for correspondence-matching. We develop a spherical alignment-guided rotation registration within each voxel to estimate the rotation of vehicle. By incorporating geometric alignment, we introduce the motion constraint into the optimization formulation to enhance the rapid and effective estimation of LiDAR's translation. Subsequently, we extract several keyframes to construct the submap and exploit an alignment from the current scan to the submap for precise pose estimation. Meanwhile, a global-scale factor graph is established to aid in the reduction of cumulative errors. In various scenes, diverse experiments have been conducted to evaluate our method. The results demonstrate that ROLO-SLAM excels in pose estimation of ground vehicles and outperforms existing state-of-the-art LiDAR SLAM frameworks.

Long Bai, Beilei Cui, Liangyu Wang et al.

Deep learning can predict depth maps and capsule ego-motion from capsule endoscopy videos, aiding in 3D scene reconstruction and lesion localization. However, the collisions of the capsule endoscopies within the gastrointestinal tract cause vibration perturbations in the training data. Existing solutions focus solely on vision-based processing, neglecting other auxiliary signals like vibrations that could reduce noise and improve performance. Therefore, we propose V$^2$-SfMLearner, a multimodal approach integrating vibration signals into vision-based depth and capsule motion estimation for monocular capsule endoscopy. We construct a multimodal capsule endoscopy dataset containing vibration and visual signals, and our artificial intelligence solution develops an unsupervised method using vision-vibration signals, effectively eliminating vibration perturbations through multimodal learning. Specifically, we carefully design a vibration network branch and a Fourier fusion module, to detect and mitigate vibration noises. The fusion framework is compatible with popular vision-only algorithms. Extensive validation on the multimodal dataset demonstrates superior performance and robustness against vision-only algorithms. Without the need for large external equipment, our V$^2$-SfMLearner has the potential for integration into clinical capsule robots, providing real-time and dependable digestive examination tools. The findings show promise for practical implementation in clinical settings, enhancing the diagnostic capabilities of doctors.

Yuxin Cui, Rui Song, Yibin Li et al.

Robust and accurate 2D/3D registration, which aligns preoperative models with intraoperative images of the same anatomy, is crucial for successful interventional navigation. To mitigate the challenge of a limited field of view in single-image intraoperative scenarios, multi-view 2D/3D registration is required by leveraging multiple intraoperative images. In this paper, we propose a novel multi-view 2D/3D rigid registration approach comprising two stages. In the first stage, a combined loss function is designed, incorporating both the differences between predicted and ground-truth poses and the dissimilarities (e.g., normalized cross-correlation) between simulated and observed intraoperative images. More importantly, additional cross-view training loss terms are introduced for both pose and image losses to explicitly enforce cross-view constraints. In the second stage, test-time optimization is performed to refine the estimated poses from the coarse stage. Our method exploits the mutual constraints of multi-view projection poses to enhance the robustness of the registration process. The proposed framework achieves a mean target registration error (mTRE) of $0.79 \pm 2.17$ mm on six specimens from the DeepFluoro dataset, demonstrating superior performance compared to state-of-the-art registration algorithms.

Haojie Shi, Max Q. -H. Meng

Recently Koopman operator has become a promising data-driven tool to facilitate real-time control for unknown nonlinear systems. It maps nonlinear systems into equivalent linear systems in embedding space, ready for real-time linear control methods. However, designing an appropriate Koopman embedding function remains a challenging task. Furthermore, most Koopman-based algorithms only consider nonlinear systems with linear control input, resulting in lousy prediction and control performance when the system is fully nonlinear with the control input. In this work, we propose an end-to-end deep learning framework to learn the Koopman embedding function and Koopman Operator together to alleviate such difficulties. We first parameterize the embedding function and Koopman Operator with the neural network and train them end-to-end with the K-steps loss function. Then, an auxiliary control network is augmented to encode the nonlinear state-dependent control term to model the nonlinearity in the control input. This encoded term is considered the new control variable instead to ensure linearity of the modeled system in the embedding system.We next deploy Linear Quadratic Regulator (LQR) on the linear embedding space to derive the optimal control policy and decode the actual control input from the control net. Experimental results demonstrate that our approach outperforms other existing methods, reducing the prediction error by order of magnitude and achieving superior control performance in several nonlinear dynamic systems like damping pendulum, CartPole, and the seven DOF robotic manipulator.

Han Ma, Chenming Li, Jianbang Liu et al.

Sampling-based path planning algorithms usually implement uniform sampling methods to search the state space. However, uniform sampling may lead to unnecessary exploration in many scenarios, such as the environment with a few dead ends. Our previous work proposes to use the promising region to guide the sampling process to address the issue. However, the predicted promising regions are often disconnected, which means they cannot connect the start and goal state, resulting in a lack of probabilistic completeness. This work focuses on enhancing the connectivity of predicted promising regions. Our proposed method regresses the connectivity probability of the edges in the x and y directions. In addition, it calculates the weight of the promising edges in loss to guide the neural network to pay more attention to the connectivity of the promising regions. We conduct a series of simulation experiments, and the results show that the connectivity of promising regions improves significantly. Furthermore, we analyze the effect of connectivity on sampling-based path planning algorithms and conclude that connectivity plays an essential role in maintaining algorithm performance.

Keyu Li, Yangxin Xu, Jian Wang et al.

Ultrasound (US) imaging is commonly used to assist in the diagnosis and interventions of spine diseases, while the standardized US acquisitions performed by manually operating the probe require substantial experience and training of sonographers. In this work, we propose a novel dual-agent framework that integrates a reinforcement learning (RL) agent and a deep learning (DL) agent to jointly determine the movement of the US probe based on the real-time US images, in order to mimic the decision-making process of an expert sonographer to achieve autonomous standard view acquisitions in spinal sonography. Moreover, inspired by the nature of US propagation and the characteristics of the spinal anatomy, we introduce a view-specific acoustic shadow reward to utilize the shadow information to implicitly guide the navigation of the probe toward different standard views of the spine. Our method is validated in both quantitative and qualitative experiments in a simulation environment built with US data acquired from 17 volunteers. The average navigation accuracy toward different standard views achieves 5.18mm/5.25deg and 12.87mm/17.49deg in the intra- and inter-subject settings, respectively. The results demonstrate that our method can effectively interpret the US images and navigate the probe to acquire multiple standard views of the spine.

Yangxin Xu, Keyu Li, Ziqi Zhao et al.

In recent years, simultaneous magnetic actuation and localization (SMAL) for active wireless capsule endoscopy (WCE) has been intensively studied to improve the efficiency and accuracy of the examination. In this paper, we propose an autonomous magnetic navigation framework for active WCE that mimics the "insertion" and "withdrawal" procedures performed by an expert physician in conventional colonoscopy, thereby enabling efficient and accurate navigation of a robotic capsule endoscope in the intestine with minimal user effort. First, the capsule is automatically propelled through the unknown intestinal environment and generate a viable path to represent the environment. Then, the capsule is autonomously navigated towards any point selected on the intestinal trajectory to allow accurate and repeated inspections of suspicious lesions. Moreover, we implement the navigation framework on a robotic system incorporated with advanced SMAL algorithms, and validate it in the navigation in various tubular environments using phantoms and an ex-vivo pig colon. Our results demonstrate that the proposed autonomous navigation framework can effectively navigate the capsule in unknown, complex tubular environments with a satisfactory accuracy, repeatability and efficiency compared with manual operation.

Chenming Li, Fei Meng, Han Ma et al.

Sampling-based planning algorithm is a powerful tool for solving planning problems in high-dimensional state spaces. In this article, we present a novel approach to sampling in the most promising regions, which significantly reduces planning time-consumption. The RRT# algorithm defines the Relevant Region based on the cost-to-come provided by the optimal forward-searching tree. However, it uses the cumulative cost of a direct connection between the current state and the goal state as the cost-to-go. To improve the path planning efficiency, we propose a batch sampling method that samples in a refined Relevant Region with a direct sampling strategy, which is defined according to the optimal cost-to-come and the adaptive cost-to-go, taking advantage of various sources of heuristic information. The proposed sampling approach allows the algorithm to build the search tree in the direction of the most promising area, resulting in a superior initial solution quality and reducing the overall computation time compared to related work. To validate the effectiveness of our method, we conducted several simulations in both $SE(2)$ and $SE(3)$ state spaces. And the simulation results demonstrate the superiorities of proposed algorithm.

Jianbang Liu, Baopu Li, Tingguang Li et al.

In this paper, we present a novel path planning algorithm to achieve fast path planning in complex environments. Most existing path planning algorithms are difficult to quickly find a feasible path in complex environments or even fail. However, our proposed framework can overcome this difficulty by using a learning-based prediction module and a sampling-based path planning module. The prediction module utilizes an auto-encoder-decoder-like convolutional neural network (CNN) to output a promising region where the feasible path probably lies in. In this process, the environment is treated as an RGB image to feed in our designed CNN module, and the output is also an RGB image. No extra computation is required so that we can maintain a high processing speed of 60 frames-per-second (FPS). Incorporated with a sampling-based path planner, we can extract a feasible path from the output image so that the robot can track it from start to goal. To demonstrate the advantage of the proposed algorithm, we compare it with conventional path planning algorithms in a series of simulation experiments. The results reveal that the proposed algorithm can achieve much better performance in terms of planning time, success rate, and path length.

Anxing Xiao, Hao Luan, Ziqi Zhao et al.

Autonomous mobile manipulation robots that can collect trolleys are widely used to liberate human resources and fight epidemics. Most prior robotic trolley collection solutions only detect trolleys with 2D poses or are merely based on specific marks and lack the formal design of planning algorithms. In this paper, we present a novel mobile manipulation system with applications in luggage trolley collection. The proposed system integrates a compact hardware design and a progressive perception and planning framework, enabling the system to efficiently and robustly collect trolleys in dynamic and complex environments. For the perception, we first develop a 3D trolley detection method that combines object detection and keypoint estimation. Then, a docking process in a short distance is achieved with an accurate point cloud plane detection method and a novel manipulator design. On the planning side, we formulate the robot's motion planning under a nonlinear model predictive control framework with control barrier functions to improve obstacle avoidance capabilities while maintaining the target in the sensors' field of view at close distances. We demonstrate our design and framework by deploying the system on actual trolley collection tasks, and their effectiveness and robustness are experimentally validated.

Keyu Li, Ye Lu, Max Q. -H. Meng

In recent years, the growing demand for more intelligent service robots is pushing the development of mobile robot navigation algorithms to allow safe and efficient operation in a dense crowd. Reinforcement learning (RL) approaches have shown superior ability in solving sequential decision making problems, and recent work has explored its potential to learn navigation polices in a socially compliant manner. However, the expert demonstration data used in existing methods is usually expensive and difficult to obtain. In this work, we consider the task of training an RL agent without employing the demonstration data, to achieve efficient and collision-free navigation in a crowded environment. To address the sparse reward navigation problem, we propose to incorporate the hindsight experience replay (HER) and curriculum learning (CL) techniques with RL to efficiently learn the optimal navigation policy in the dense crowd. The effectiveness of our method is validated in a simulated crowd-robot coexisting environment. The results demonstrate that our method can effectively learn human-aware navigation without requiring additional demonstration data.

Fan Bai, Fei Meng, Jianbang Liu et al.

Non-prehensile multi-object rearrangement is a robotic task of planning feasible paths and transferring multiple objects to their predefined target poses without grasping. It needs to consider how each object reaches the target and the order of object movement, which significantly deepens the complexity of the problem. To address these challenges, we propose a hierarchical policy to divide and conquer for non-prehensile multi-object rearrangement. In the high-level policy, guided by a designed policy network, the Monte Carlo Tree Search efficiently searches for the optimal rearrangement sequence among multiple objects, which benefits from imitation and reinforcement. In the low-level policy, the robot plans the paths according to the order of path primitives and manipulates the objects to approach the goal poses one by one. We verify through experiments that the proposed method can achieve a higher success rate, fewer steps, and shorter path length compared with the state-of-the-art.

Haojie Shi, Bo Zhou, Hongsheng Zeng et al.

Recently reinforcement learning (RL) has emerged as a promising approach for quadrupedal locomotion, which can save the manual effort in conventional approaches such as designing skill-specific controllers. However, due to the complex nonlinear dynamics in quadrupedal robots and reward sparsity, it is still difficult for RL to learn effective gaits from scratch, especially in challenging tasks such as walking over the balance beam. To alleviate such difficulty, we propose a novel RL-based approach that contains an evolutionary foot trajectory generator. Unlike prior methods that use a fixed trajectory generator, the generator continually optimizes the shape of the output trajectory for the given task, providing diversified motion priors to guide the policy learning. The policy is trained with reinforcement learning to output residual control signals that fit different gaits. We then optimize the trajectory generator and policy network alternatively to stabilize the training and share the exploratory data to improve sample efficiency. As a result, our approach can solve a range of challenging tasks in simulation by learning from scratch, including walking on a balance beam and crawling through the cave. To further verify the effectiveness of our approach, we deploy the controller learned in the simulation on a 12-DoF quadrupedal robot, and it can successfully traverse challenging scenarios with efficient gaits.

Yangxin Xu, Keyu Li, Ziqi Zhao et al.

Currently used wireless capsule endoscopy (WCE) is limited in terms of inspection time and flexibility since the capsule is passively moved by peristalsis and cannot be accurately positioned. Different methods have been proposed to facilitate active locomotion of WCE based on simultaneous magnetic actuation and localization technologies. In this work, we investigate the trajectory following problem of a robotic capsule under rotating magnetic actuation in a tubular environment, in order to realize safe, efficient and accurate inspection of the intestine at given points using wireless capsule endoscopes. Specifically, four trajectory following strategies are developed based on the PD controller, adaptive controller, model predictive controller and robust multi-stage model predictive controller. Moreover, our method takes into account the uncertainty in the intestinal environment by modeling the intestinal peristalsis and friction during the controller design. We validate our methods in simulation as well as in real-world experiments in various tubular environments, including plastic phantoms with different shapes and an ex-vivo pig colon. The results show that our approach can effectively actuate a reciprocally rotating capsule to follow a desired trajectory in complex tubular environments, thereby having the potential to enable accurate and repeatable inspection of the intestine for high-quality diagnosis.

Yangxin Xu, Keyu Li, Ziqi Zhao et al.

Simultaneous Magnetic Actuation and Localization (SMAL) is a promising technology for active wireless capsule endoscopy (WCE). In this paper, an adaptive SMAL system is presented to efficiently propel and precisely locate a capsule in a tubular environment with complex shapes. In order to track the capsule with high localization accuracy and update frequency in a large workspace, we propose a mechanism that can automatically activate a sub-array of sensors with the optimal layout during the capsule movement. The improved multiple objects tracking (IMOT) method is simplified and adapted to our system to estimate the 6-D pose of the capsule in real time. Also, we study the locomotion of a magnetically actuated capsule in a tubular environment, and formulate a method to adaptively adjust the pose of the actuator to improve the propulsion efficiency. Our presented methods are applicable to other permanent magnet-based SMAL systems, and help to improve the actuation efficiency of active WCE. We verify the effectiveness of our proposed system in extensive experiments on phantoms and ex-vivo animal organs. The results demonstrate that our system can achieve convincing performance compared with the state-of-the-art ones in terms of actuation efficiency, workspace size, robustness, localization accuracy and update frequency.

Yangxin Xu, Keyu Li, Ziqi Zhao et al.

Active wireless capsule endoscopy (WCE) based on simultaneous magnetic actuation and localization (SMAL) techniques holds great promise for improving diagnostic accuracy, reducing examination time and relieving operator burden. To date, the rotating magnetic actuation methods have been constrained to use a continuously rotating permanent magnet. In this paper, we first propose the reciprocally rotating magnetic actuation (RRMA) approach for active WCE to enhance patient safety. We first show how to generate a desired reciprocally rotating magnetic field for capsule actuation, and provide a theoretical analysis of the potential risk of causing volvulus due to the capsule motion. Then, an RRMA-based SMAL workflow is presented to automatically propel a capsule in an unknown tubular environment. We validate the effectiveness of our method in real-world experiments to automatically propel a robotic capsule in an ex-vivo pig colon. The experiment results show that our approach can achieve efficient and robust propulsion of the capsule with an average moving speed of $2.48 mm/s$ in the pig colon, and demonstrate the potential of using RRMA to enhance patient safety, reduce the inspection time, and improve the clinical acceptance of this technology.

Kaiwei Che, Chengwei Ye, Yibing Yao et al.

Colonoscopy is a standard imaging tool for visualizing the entire gastrointestinal (GI) tract of patients to capture lesion areas. However, it takes the clinicians excessive time to review a large number of images extracted from colonoscopy videos. Thus, automatic detection of biological anatomical landmarks within the colon is highly demanded, which can help reduce the burden of clinicians by providing guidance information for the locations of lesion areas. In this article, we propose a novel deep learning-based approach to detect biological anatomical landmarks in colonoscopy videos. First, raw colonoscopy video sequences are pre-processed to reject interference frames. Second, a ResNet-101 based network is used to detect three biological anatomical landmarks separately to obtain the intermediate detection results. Third, to achieve more reliable localization of the landmark periods within the whole video period, we propose to post-process the intermediate detection results by identifying the incorrectly predicted frames based on their temporal distribution and reassigning them back to the correct class. Finally, the average detection accuracy reaches 99.75\%. Meanwhile, the average IoU of 0.91 shows a high degree of similarity between our predicted landmark periods and ground truth. The experimental results demonstrate that our proposed model is capable of accurately detecting and localizing biological anatomical landmarks from colonoscopy videos.

Xiaohan Xing, Yuenan Hou, Hang Li et al.

The amount of medical images for training deep classification models is typically very scarce, making these deep models prone to overfit the training data. Studies showed that knowledge distillation (KD), especially the mean-teacher framework which is more robust to perturbations, can help mitigate the over-fitting effect. However, directly transferring KD from computer vision to medical image classification yields inferior performance as medical images suffer from higher intra-class variance and class imbalance. To address these issues, we propose a novel Categorical Relation-preserving Contrastive Knowledge Distillation (CRCKD) algorithm, which takes the commonly used mean-teacher model as the supervisor. Specifically, we propose a novel Class-guided Contrastive Distillation (CCD) module to pull closer positive image pairs from the same class in the teacher and student models, while pushing apart negative image pairs from different classes. With this regularization, the feature distribution of the student model shows higher intra-class similarity and inter-class variance. Besides, we propose a Categorical Relation Preserving (CRP) loss to distill the teacher's relational knowledge in a robust and class-balanced manner. With the contribution of the CCD and CRP, our CRCKD algorithm can distill the relational knowledge more comprehensively. Extensive experiments on the HAM10000 and APTOS datasets demonstrate the superiority of the proposed CRCKD method.

Zhaoting Li, Tingguang Li, Jiankun Wang et al.

Being able to explore unknown environments is a requirement for fully autonomous robots. Many learning-based methods have been proposed to learn an exploration strategy. In the frontier-based exploration, learning algorithms tend to learn the optimal or near-optimal frontier to explore. Most of these methods represent the environments as fixed size images and take these as inputs to neural networks. However, the size of environments is usually unknown, which makes these methods fail to generalize to real world scenarios. To address this issue, we present a novel state representation method based on 4D point-clouds-like information, including the locations, frontier, and distance information. We also design a neural network that can process these 4D point-clouds-like information and generate the estimated value for each frontier. Then this neural network is trained using the typical reinforcement learning framework. We test the performance of our proposed method by comparing it with other five methods and test its scalability on a map that is much larger than maps in the training set. The experiment results demonstrate that our proposed method needs shorter average traveling distances to explore whole environments and can be adopted in maps with arbitrarily sizes.

Kuanqi Cai, Weinan Chen, Chaoqun Wang et al.

Mobile robots have become more and more popular in large-scale and crowded environments, such as airports, shopping malls, etc. However, due to sparse landmarks and crowd noise, localization in this environment is a great challenge. Furthermore, it is unreliable for the robot to navigate safely in crowds while considering human comfort. Thus, how to navigate safely with localization precision in that environment is a critical problem. To solve this problem, we proposed a curiosity-based framework that can find an effective path with the consideration of human comfort and crowds, localization uncertainty, and the cost-to-go to the target. Three parts are involved in the proposed framework: the distance assessment module, the Curiosity for Positive Content (CPC), namely information-rich areas, and the Curiosity for Negative Content (CNC), namely crowded areas. CPC is introduced when the real-time localization uncertainty evaluation is not satisfied. This factor is predicted through the propagation of uncertainty along the candidate trajectory to provoke the robot to approach localization-referenced landmarks. The Human Comfort and Crowd Density Map (HCCDM) based on the Gaussian Mixture Model (GMM) is established to calculate CNC, which drives the robot to bypass the crowd and consider human comfort. The evaluation is conducted in a series of large-scale and crowded environments. The results show that our method can find a feasible path that can consider the localization uncertainty while simultaneously avoiding the crowded area.

HaoChih Lin, Baopu Li, Xin Zhou et al.

Interactions with either environments or expert policies during training are needed for most of the current imitation learning (IL) algorithms. For IL problems with no interactions, a typical approach is Behavior Cloning (BC). However, BC-like methods tend to be affected by distribution shift. To mitigate this problem, we come up with a Robust Model-Based Imitation Learning (RMBIL) framework that casts imitation learning as an end-to-end differentiable nonlinear closed-loop tracking problem. RMBIL applies Neural ODE to learn a precise multi-step dynamics and a robust tracking controller via Nonlinear Dynamics Inversion (NDI) algorithm. Then, the learned NDI controller will be combined with a trajectory generator, a conditional VAE, to imitate an expert's behavior. Theoretical derivation shows that the controller network can approximate an NDI when minimizing the training loss of Neural ODE. Experiments on Mujoco tasks also demonstrate that RMBIL is competitive to the state-of-the-art generative adversarial method (GAIL) and achieves at least 30% performance gain over BC in uneven surfaces.

Keyu Li, Jian Wang, Yangxin Xu et al.

Autonomous ultrasound (US) acquisition is an important yet challenging task, as it involves interpretation of the highly complex and variable images and their spatial relationships. In this work, we propose a deep reinforcement learning framework to autonomously control the 6-D pose of a virtual US probe based on real-time image feedback to navigate towards the standard scan planes under the restrictions in real-world US scans. Furthermore, we propose a confidence-based approach to encode the optimization of image quality in the learning process. We validate our method in a simulation environment built with real-world data collected in the US imaging of the spine. Experimental results demonstrate that our method can perform reproducible US probe navigation towards the standard scan plane with an accuracy of $4.91mm/4.65^\circ$ in the intra-patient setting, and accomplish the task in the intra- and inter-patient settings with a success rate of $92\%$ and $46\%$, respectively. The results also show that the introduction of image quality optimization in our method can effectively improve the navigation performance.

Tianyi Zhang, Jiankun Wang, Max Q. -H. Meng

Sampling-based path planning is a popular methodology for robot path planning. With a uniform sampling strategy to explore the state space, a feasible path can be found without the complex geometric modeling of the configuration space. However, the quality of initial solution is not guaranteed and the convergence speed to the optimal solution is slow. In this paper, we present a novel image-based path planning algorithm to overcome these limitations. Specifically, a generative adversarial network (GAN) is designed to take the environment map (denoted as RGB image) as the input without other preprocessing works. The output is also an RGB image where the promising region (where a feasible path probably exists) is segmented. This promising region is utilized as a heuristic to achieve nonuniform sampling for the path planner. We conduct a number of simulation experiments to validate the effectiveness of the proposed method, and the results demonstrate that our method performs much better in terms of the quality of initial solution and the convergence speed to the optimal solution. Furthermore, apart from the environments similar to the training set, our method also works well on the environments which are very different from the training set.

Zhaoting Li, Jiankun Wang, Max Q. -H. Meng

Robot path planning is difficult to solve due to the contradiction between optimality of results and complexity of algorithms, even in 2D environments. To find an optimal path, the algorithm needs to search all the state space, which costs a lot of computation resource. To address this issue, we present a novel recurrent generative model (RGM) which generates efficient heuristic to reduce the search efforts of path planning algorithm. This RGM model adopts the framework of general generative adversarial networks (GAN), which consists of a novel generator that can generate heuristic by refining the outputs recurrently and two discriminators that check the connectivity and safety properties of heuristic. We test the proposed RGM module in various 2D environments to demonstrate its effectiveness and efficiency. The results show that the RGM successfully generates appropriate heuristic in both seen and new unseen maps with a high accuracy, demonstrating the good generalization ability of this model. We also compare the rapidly-exploring random tree star (RRT*) with generated heuristic and the conventional RRT* in four different maps, showing that the generated heuristic can guide the algorithm to find both initial and optimal solution in a faster and more efficient way.

Nachuan Ma, Jiankun Wang, Max Q. -H. Meng

Path planning plays an important role in autonomous robot systems. Effective understanding of the surrounding environment and efficient generation of optimal collision-free path are both critical parts for solving path planning problem. Although conventional sampling-based algorithms, such as the rapidly-exploring random tree (RRT) and its improved optimal version (RRT*), have been widely used in path planning problems because of their ability to find a feasible path in even complex environments, they fail to find an optimal path efficiently. To solve this problem and satisfy the two aforementioned requirements, we propose a novel learning-based path planning algorithm which consists of a novel generative model based on the conditional generative adversarial networks (CGAN) and a modified RRT* algorithm (denoted by CGANRRT*). Given the map information, our CGAN model can generate an efficient possibility distribution of feasible paths, which can be utilized by the CGAN-RRT* algorithm to find the optimal path with a non-uniform sampling strategy. The CGAN model is trained by learning from ground truth maps, each of which is generated by putting all the results of executing RRT algorithm 50 times on one raw map. We demonstrate the efficient performance of this CGAN model by testing it on two groups of maps and comparing CGAN-RRT* algorithm with conventional RRT* algorithm.

Jiahui Lin, Tong Zhou, Delong Zhu et al.

This paper presents a search-based partial motion planner to generate dynamically feasible trajectories for car-like robots in highly dynamic environments. The planner searches for smooth, safe, and near-time-optimal trajectories by exploring a state graph built on motion primitives, which are generated by discretizing the time dimension and the control space. To enable fast online planning, we first propose an efficient path searching algorithm based on the aggregation and pruning of motion primitives. We then propose a fast collision checking algorithm that takes into account the motions of moving obstacles. The algorithm linearizes relative motions between the robot and obstacles and then checks collisions by comparing a point-line distance. Benefiting from the fast searching and collision checking algorithms, the planner can effectively and safely explore the state-time space to generate near-time-optimal solutions. The results through extensive experiments show that the proposed method can generate feasible trajectories within milliseconds while maintaining a higher success rate than up-to-date methods, which significantly demonstrates its advantages.

Delong Zhu, Tong Zhou, Jiahui Lin et al.

Online state-time trajectory planning in highly dynamic environments remains an unsolved problem due to the unpredictable motions of moving obstacles and the curse of dimensionality from the state-time space. Existing state-time planners are typically implemented based on randomized sampling approaches or path searching on discretized state graph. The smoothness, path clearance, and planning efficiency of these planners are usually not satisfying. In this work, we propose a gradient-based planner over the state-time space for online trajectory generation in highly dynamic environments. To enable the gradient-based optimization, we propose a Timed-ESDT that supports distance and gradient queries with state-time keys. Based on the Timed-ESDT, we also define a smooth prior and an obstacle likelihood function that is compatible with the state-time space. The trajectory planning is then formulated to a MAP problem and solved by an efficient numerical optimizer. Moreover, to improve the optimality of the planner, we also define a state-time graph and then conduct path searching on it to find a better initialization for the optimizer. By integrating the graph searching, the planning quality is significantly improved. Experiment results on simulated and benchmark datasets show that our planner can outperform the state-of-the-art methods, demonstrating its significant advantages over the traditional ones.

Kuanqi Cai, Chaoqun Wang, Jiyu Cheng et al.

There are many challenges for robot navigation in densely populated dynamic environments. This paper presents a survey of the path planning methods for robot navigation in dense environments. Particularly, the path planning in the navigation framework of mobile robots is composed of global path planning and local path planning, with regard to the planning scope and the executability. Within this framework, the recent progress of the path planning methods is presented in the paper, while examining their strengths and weaknesses. Notably, the recently developed Velocity Obstacle method and its variants that serve as the local planner are analyzed comprehensively. Moreover, as a model-free method that is widely used in current robot applications, the reinforcement learning-based path planning algorithms are detailed in this paper.

Delong Zhu, Jianbang Liu, Nachuan Ma et al.

Elevator button recognition is considered an indispensable function for enabling the autonomous elevator operation of mobile robots. However, due to unfavorable image conditions and various image distortions, the recognition accuracy remains to be improved. In this paper, we present a novel algorithm that can autonomously correct perspective distortions of elevator panel images. The algorithm first leverages the Gaussian Mixture Model (GMM) to conduct a grid fitting process based on button recognition results, then utilizes the estimated grid centers as reference features to estimate camera motions for correcting perspective distortions. The algorithm performs on a single image autonomously and does not need explicit feature detection or feature matching procedure, which is much more robust to noises and outliers than traditional feature-based geometric approaches. To verify the effectiveness of the algorithm, we collect an elevator panel dataset of 50 images captured from different angles of view. Experimental results show that the proposed algorithm can accurately estimate camera motions and effectively remove perspective distortions.

Teng Li, Chaoqun Wang, Max Q. -H. Meng et al.

Unmanned Aerial Vehicles (UAVs) have been implemented for environmental monitoring by using their capabilities of mobile sensing, autonomous navigation, and remote operation. However, in real-world applications, the limitations of on-board resources (e.g., power supply) of UAVs will constrain the coverage of the monitored area and the number of the acquired samples, which will hinder the performance of field estimation and mapping. Therefore, the issue of constrained resources calls for an efficient sampling planner to schedule UAV-based sensing tasks in environmental monitoring. This paper presents a mission planner of coverage sampling and path planning for a UAV-enabled mobile sensor to effectively explore and map an unknown environment that is modeled as a random field. The proposed planner can generate a coverage path with an optimal coverage density for exploratory sampling, and the associated energy cost is subjected to a power supply constraint. The performance of the developed framework is evaluated and compared with the existing state-of-the-art algorithms, using a real-world dataset that is collected from an environmental monitoring program as well as physical field experiments. The experimental results illustrate the reliability and accuracy of the presented coverage sampling planner in a prior survey for environmental exploration and field mapping.

Tingguang Li, Danny Ho, Chenming Li et al.

As one of the most promising areas, mobile robots draw much attention these years. Current work in this field is often evaluated in a few manually designed scenarios, due to the lack of a common experimental platform. Meanwhile, with the recent development of deep learning techniques, some researchers attempt to apply learning-based methods to mobile robot tasks, which requires a substantial amount of data. To satisfy the underlying demand, in this paper we build HouseExpo, a large-scale indoor layout dataset containing 35,126 2D floor plans including 252,550 rooms in total. Together we develop Pseudo-SLAM, a lightweight and efficient simulation platform to accelerate the data generation procedure, thereby speeding up the training process. In our experiments, we build models to tackle obstacle avoidance and autonomous exploration from a learning perspective in simulation as well as real-world experiments to verify the effectiveness of our simulator and dataset. All the data and codes are available online and we hope HouseExpo and Pseudo-SLAM can feed the need for data and benefits the whole community.

Chaoqun Wang, Delong Zhu, Teng Li et al.

In this paper, we propose an integrated framework for the autonomous robotic exploration in indoor environments. Specially, we present a hybrid map, named Semantic Road Map (SRM), to represent the topological structure of the explored environment and facilitate decision-making in the exploration. The SRM is built incrementally along with the exploration process. It is a graph structure with collision-free nodes and edges that are generated within the sensor coverage. Moreover, each node has a semantic label and the expected information gain at that location. Based on the concise SRM, we present a novel and effective decision-making model to determine the next-best-target (NBT) during the exploration. The model concerns the semantic information, the information gain, and the path cost to the target location. We use the nodes of SRM to represent the candidate targets, which enables the target evaluation to be performed directly on the SRM. With the SRM, both the information gain of a node and the path cost to the node can be obtained efficiently. Besides, we adopt the cross-entropy method to optimize the path to make it more informative. We conduct experimental studies in both simulated and real-world environments, which demonstrate the effectiveness of the proposed method.

Tingguang Li, Jin Pan, Delong Zhu et al.

To achieve scenario intelligence, humans must transfer knowledge to robots by developing goal-oriented algorithms, which are sometimes insensitive to dynamically changing environments. While deep reinforcement learning achieves significant success recently, it is still extremely difficult to be deployed in real robots directly. In this paper, we propose a hybrid structure named Option-Interruption in which human knowledge is embedded into a hierarchical reinforcement learning framework. Our architecture has two key components: options, represented by existing human-designed methods, can significantly speed up the training process and interruption mechanism, based on learnable termination functions, enables our system to quickly respond to the external environment. To implement this architecture, we derive a set of update rules based on policy gradient methods and present a complete training process. In the experiment part, our method is evaluated in Four-room navigation and exploration task, which shows the efficiency and flexibility of our framework.

Kun Li, Max Q. -H. Meng

In a robot-centered smart home, the robot observes the home states with its own sensors, and then it can change certain object states according to an operator's commands for remote operations, or imitate the operator's behaviors in the house for autonomous operations. To model the robot's imitation of the operator's behaviors in a dynamic indoor environment, we use multi-relational chains to describe the changes of environment states, and apply inverse reinforcement learning to encoding the operator's behaviors with a learned reward function. We implement this approach with a mobile robot, and do five experiments to include increasing training days, object numbers, and action types. Besides, a baseline method by directly recording the operator's behaviors is also implemented, and comparison is made on the accuracy of home state evaluation and the accuracy of robot action selection. The results show that the proposed approach handles dynamic environment well, and guides the robot's actions in the house more accurately.

Kun Li, Max Q. -H. Meng

To learn object models for robotic manipulation, unsupervised methods cannot provide accurate object structural information and supervised methods require a large amount of manually labeled training samples, thus interactive object segmentation is developed to automate object modeling. In this article, we formulate a novel dynamic process for interactive object segmentation, and develop a solution based on particle filter and active learning so that a robot can manipulate and learn object structures incrementally and automatically. We demonstrate our method with a humanoidrobot on different types of objects, and compare its segmentation performancewith established methods on selected objects. The result shows that our approach allows more accurate object modeling and reveals richer object structural information.