Recent approaches for few-shot 3D point cloud semantic segmentation typically require a two-stage learning process, i.e., a pre-training stage followed by a few-shot training stage. While effective, these methods face overreliance on pre-training, which hinders model flexibility and adaptability. Some models tried to avoid pre-training yet failed to capture ample information. In addition, current approaches focus on visual information in the support set and neglect or do not fully exploit other useful data, such as textual annotations. This inadequate utilization of support information impairs the performance of the model and restricts its zero-shot ability. To address these limitations, we present a novel pre-training-free network, named Efficient Point Cloud Semantic Segmentation for Few- and Zero-shot scenarios. Our EPSegFZ incorporates three key components. A Prototype-Enhanced Registers Attention (ProERA) module and a Dual Relative Positional Encoding (DRPE)-based cross-attention mechanism for improved feature extraction and accurate query-prototype correspondence construction without pre-training. A Language-Guided Prototype Embedding (LGPE) module that effectively leverages textual information from the support set to improve few-shot performance and enable zero-shot inference.Extensive experiments show that our method outperforms the state-of-the-art method by 5.68% and 3.82% on the S3DIS and ScanNet benchmarks, respectively.

Recent 6D pose estimation methods demonstrate notable performance but still face some practical limitations. For instance, many of them rely heavily on sensor depth, which may fail with challenging surface conditions, such as transparent or highly reflective materials. In the meantime, RGB-based solutions provide less robust matching performance in low-light and texture-less scenes due to the lack of geometry information. Motivated by these, we propose **SingRef6D**, a lightweight pipeline requiring only a **single RGB** image as a reference, eliminating the need for costly depth sensors, multi-view image acquisition, or training view synthesis models and neural fields. This enables SingRef6D to remain robust and capable even under resource-limited settings where depth or dense templates are unavailable. Our framework incorporates two key innovations. First, we propose a token-scaler-based fine-tuning mechanism with a novel optimization loss on top of Depth-Anything v2 to enhance its ability to predict accurate depth, even for challenging surfaces. Our results show a 14.41% improvement (in $\delta_{1.05}$) on REAL275 depth prediction compared to Depth-Anything v2 (with fine-tuned head). Second, benefiting from depth availability, we introduce a depth-aware matching process that effectively integrates spatial relationships within LoFTR, enabling our system to handle matching for challenging materials and lighting conditions. Evaluations of pose estimation on the REAL275, ClearPose, and Toyota-Light datasets show that our approach surpasses state-of-the-art methods, achieving a 6.1% improvement in average recall.

Three-dimensional point cloud semantic segmentation is a fundamental task in computer vision. As the fully supervised approaches suffer from the generalization issue with limited data, few-shot point cloud segmentation models have been proposed to address the flexible adaptation. Nevertheless, due to the class-agnostic nature of the few-shot pretraining, its pretrained feature extractor is hard to capture the class-related intrinsic and abstract information. Therefore, we introduce the new concept of shallow and deep similarities and propose a shallow-deep similarity learning network (SDSimPoint) that aims to learn both shallow (superficial geometry, color, etc.) and deep similarities (intrinsic context and semantics, etc.) between the support and query samples, thereby boosting the performance. Moreover, we design a beyond-episode attention module (BEAM) to enlarge the region of the attention mechanism from a single episode to the entire dataset by utilizing the memory units, which enhances the extraction ability to better capture the shallow and deep similarities. Furthermore, our distance metric function is learnable in the proposed framework, which can better adapt to complex data distributions. Our proposed SDSimPoint consistently demonstrates substantial improvements compared to baseline approaches across various datasets in diverse few-shot point cloud semantic segmentation settings.

This paper presents an effective few-shot point cloud semantic segmentation approach for real-world applications. Existing few-shot segmentation methods on point cloud heavily rely on the fully-supervised pretrain with large annotated datasets, which causes the learned feature extraction bias to those pretrained classes. However, as the purpose of few-shot learning is to handle unknown/unseen classes, such class-specific feature extraction in pretrain is not ideal to generalize into new classes for few-shot learning. Moreover, point cloud datasets hardly have a large number of classes due to the annotation difficulty. To address these issues, we propose a contrastive self-supervision framework for few-shot learning pretrain, which aims to eliminate the feature extraction bias through class-agnostic contrastive supervision. Specifically, we implement a novel contrastive learning approach with a learnable augmentor for a 3D point cloud to achieve point-wise differentiation, so that to enhance the pretrain with managed overfitting through the self-supervision. Furthermore, we develop a multi-resolution attention module using both the nearest and farthest points to extract the local and global point information more effectively, and a center-concentrated multi-prototype is adopted to mitigate the intra-class sparsity. Comprehensive experiments are conducted to evaluate the proposed approach, which shows our approach achieves state-of-the-art performance. Moreover, a case study on practical CAM/CAD segmentation is presented to demonstrate the effectiveness of our approach for real-world applications.

Warehouse management is a critical element in the supply chain. The rise of e-commerce demands ‘any-mix any-volume’ customized and personalized orders. Due to the variety of products in ‘any-mix any-volume’ scenario the warehouse operations have become complex. The advent of multi-channel commerce has reduced the minimum order quantity (MOQ), claiming frequent changes. The ‘any-mix any-volume’ operations require flexible automation for product storage, retrieval, packing and shipping. Seamless operations of multiple devices are essential for automating flexible warehouses. For effective flexible operations, the Warehouse Management System (WMS) requires controlling the automation devices and associated auxiliary systems. Heterogenous automation devices with distinct communication protocols, data formats and connectivity are challenges for WMS centered control. An interoperable WMS can enable seamless communication and data exchange among devices. In this work, the interoperability of the WMS and various aspects of interoperability of engineering systems are presented. Different WMS system designs are considered and evaluated for the interoperability requirements. A framework for evaluating the interoperability of a WMS is proposed which is validated through experimental trials at an industry grade warehouse.

Modern CAM/CAD workflows can benefit greatly from precise 3D semantic segmentation, which contributes to reducing the defect rate of work-pieces manufactured by computer-controlled CNCs and ultimately enhancing work efficiency. The majority of existing approaches for 3D object segmentation heavily rely on fully-supervised learning, where AI models are trained using extensive datasets with annotations. However, these models often exhibit unsatisfactory performance when confronted with scenarios characterized by high mixture but low volume. This means they struggle to accurately segment novel classes that were not encountered during training. In this paper, we introduce and formulate a noteworthy approach based on few-shot learning, which incorporates Sequential Dual Attention (SDA) and feature enhancement techniques. Our method aims to achieve effective semantic segmentation of point clouds in the context of CAM/CAD workflows. Unlike other few-shot models that solely adopt self-attention or lack attention, our SDA captures features at both the channel and spatial levels. Additionally, we design a non-parametric feature enhancement block to enhance the recognizability of each class in the feature space. Our proposed approach consistently demonstrates substantial enhancements in various few-shot point cloud semantic segmentation scenarios across two datasets, outperforming baseline methods.

In this article, we present a database of multimodal communication features extracted from debate speeches in the 2019 North American Universities Debate Championships (NAUDC). Feature sets were extracted from the visual (facial expression, gaze, and head pose), audio (PRAAT), and textual (word sentiment and linguistic category) modalities of raw video recordings of competitive collegiate debaters (N=716 6-minute recordings from 140 unique debaters). Each speech has an associated competition debate score (range: 67-96) from experienced judges as well as competitor demographic and per-round reflection surveys. We observe the fully multimodal model performs best in comparison to models trained on various compositions of individual modalities. We also find that the weights of some features (such as the expression ofjoyand the use of the word ”we”) change in direction between the aforementioned models. We use these results to highlight the value of a multimodal dataset for studying competitive, collegiate debate.

3D part segmentation is an essential step in advanced CAM/CAD workflow. Precise 3D segmentation contributes to lower defective rate of work-pieces produced by the manufacturing equipment (such as computer controlled CNCs), thereby improving work efficiency and attaining the attendant economic benefits. A large class of existing works on 3D model segmentation are mostly based on fully-supervised learning, which trains the AI models with large, annotated datasets. However, the disadvantage is that the resulting models from the fully-supervised learning methodology are highly reliant on the completeness (or otherwise) of the available dataset, and its generalization ability is relatively poor to new unknown/unseen segmentation types (i.e., further additional so-called novel classes). In this work, we propose and develop a noteworthy few-shot learning-based approach for effective part segmentation in CAM/CAD; and this is designed to significantly enhance its generalization ability, and our development also aims to flexibly adapt to new segmentation tasks by using only relatively rather few samples. As a result, it not only reduces the requirements for the usually unattainable and exhaustive completeness of supervision datasets, but also improves the flexibility for real-world applications. In the development, drawing inspiration from the pertinent and interesting work described in the open literature as the attMPTI network, we propose and develop a multi-prototype approach (with self-attention mechanics) for few-shot point cloud part segmentation. As further improvement and innovation, we additionally adopt the transform net and the center loss block in the network. These characteristics serve to improve the comprehension for 3D features of the various possible instances of the whole work-piece and ensure the close distribution of the same class in feature space. Moreover, our approach stores data in the point cloud format that reduces space consumption, and which also makes the various procedures involved have significantly easier read and edit access (thus improving efficiency and effectiveness and lowering costs).

While designing control for a class of underactuated mechanical systems (UMSs), the uncertainty and the prescribed nonholonomic tracking trajectories should be taken into consideration. Uncertainty considered in this article is time varying and bounded, and the bound of uncertainty is described using the fuzzy set theory, namely, fuzzy UMSs. An analytical dynamics-based view is taken in which the prescribed tracking trajectories are viewed as servo constraints which can be linear, nonlinear, holonomic, and nonholonomic. Using this view, a novel closed form solution of adaptive robust control is found with leakage type adaptive law to guarantee deterministic system performance, including uniform boundedness and uniform ultimate boundedness. In order to find the optimal dual gain parameters of the designed control, a two-player cooperative game is proposed for which the Pareto optimality can always be guaranteed. The effectiveness of the proposed control is shown through numerical simulation of a two-wheeled inverted pendulum vehicle.

This article investigates the trajectory tracking problem of underactuated mechanical systems (UMSs) with companion nonholonomic servo constraints and uncertainties. For such motion tasks, the existing approaches in the literature attempt unrealistically to furnish a reliable closed-form solution, rendering it difficult to have high-quality tracking performance with theoretical support. In addition, the uncertainties typically pose substantial difficulty in the controller synthesis. Here, by invoking the methodology of fuzzy sets, the uncertainties in the UMSs are elegantly represented; and with this, the formulation becomes such that a closer link between the uncertain dynamical model of the UMSs and the real world is established. The reference trajectories are regarded appropriately as servo constraints, and subsequently an adaptive robust controller is designed to accomplish the trajectory tracking task from a specific viewpoint of servo constraint tracking. As supported by rigorous proofs, the closed-form solution to the proposed controller is obtained with guaranteed Lyapunov stability. Leveraging on the closed-form solution, the global optimizer to the controller gain parameter can be determined, which is shown to exhibit several important properties including existence and uniqueness. Finally, a numerical example is presented to demonstrate the effectiveness of the designed method.

For a specific class of under-actuated mechanical systems, non-holonomic servo constraints and model uncertainties are usually encountered. For such systems, this paper investigates the design of an adaptive robust controller with parameter optimization. A tighter link between the fuzzy set theory and the control of UMSs is bridged appropriately. Based on the UMSs with fuzzy information, an adaptive robust control method is then designed, and an analytical solution of the control input is determined, even if the servo constraints are non-holonomic. Furthermore, a concomitant parameter in the designed controller is analyzed, and a feasible controller admitting the optimal performance can be determined by minimizing a predefined performance index, such that the deterministic system performance can be ensured to be at a satisfying level. As supported by rigorous proofs, the existence and the uniqueness of the global solution to the optimization problem are presented. Finally, a numerical experiment is implemented to demonstrate the effectiveness of the proposed control design methodology.

To address the problem of the non-holonomic reference trajectory in trajectory tracking controller design for mechanical systems, we design a novel RBF-Udwadia controller in this paper. The framework of the Udwadia controller is employed to design the controller, which helps to deal with the non-holonomic reference trajectory. The radial basis function (RBF) neural network is employed to approximately model the uncertainty. The stability of the designed controller is analyzed by the Lyapunov method, and the effectiveness of the designed controller is verified by a numerical experiment.

In this paper, a neural network-based (NN-based) integral sliding mode control approach is presented for a piezoelectric ultrasonic motor. The precision motion performance of the motor can be adversely affected in the presence of nonlinearities including friction and disturbance, as well as parameters uncertainties. Integral sliding mode control is effective in dealing with uncertainties and disturbances. To achieve better performance on tracking desired motion trajectories, a neural network structure with modified jump basis functions are used to model and compensate the discontinuous friction in the motor control systems. This structure can approximate friction with high accuracy but require few NN nodes. Stability of the proposed control strategy is analyzed. The simulation studies are provided to demonstrate the precise tracking performance of the proposed control scheme.

We present the design of an online social skills development interface for teenagers with autism spectrum disorder (ASD). The interface is intended to enable private conversation practice anywhere, anytime using a web-browser. Users converse informally with a virtual agent, receiving feedback on nonverbal cues in realtime, and summary feedback. The prototype was developed in consultation with an expert UX designer, two psychologists, and a pediatrician. Using the data from 47 individuals, feedback and dialogue generation were automated using a hidden Markov model and a schema-driven dialogue manager capable of handling multi-topic conversations. We conducted a study with nine high-functioning ASD teenagers. Through a thematic analysis of post-experiment interviews, identified several key design considerations, notably:

The dual-drive H-gantry is widely used for high-speed, high-precision Cartesian motion. Compared with the conventional rigid-linked design, the flexure-linked counterpart is able to prevent the damage of joints for its smaller interaxial coupling force. However, there are still barriers to further push up its precision, such as parametric uncertainties due to the inaccurate dynamical model, the possible induced vibration during high-speed motion, and the decentralized control structure required by industries. To maintain the tracking precision of carriages and minimize the vibration of the end effector, we aim to optimize parameters in decentralized controllers with choices of flexure pieces. We find that such decentralized feedback structure yields some uncontrollable but stabilizable states in the closed-loop system, and no direct solution from solving the algebraic Riccati equation is available in this case. Such structural constraint, together with constraints due to stability requirement and model uncertainties facilitates us to formulate an H2guaranteed cost control problem within a projected convex domain. From here, efficient numerical procedures are developed to obtain the global optimum by iterative linear programming. The real-time experiment validates the optimality and the robustness of the proposed method.

In this paper, we propose novel edge and corner detection algorithms for unorganized point clouds. Our edge detection method evaluates symmetry in a local neighborhood and uses an adaptive density based threshold to differentiate 3D edge points. We extend this algorithm to propose a novel corner detector that clusters curvature vectors and uses their geometrical statistics to classify a point as corner. We perform rigorous evaluation of the algorithms on RGB-D semantic segmentation and 3D washer models from the ShapeNet dataset and report higher precision and recall scores. Finally, we also demonstrate how our edge and corner detectors can be used as a novel approach towards automatic weld seam detection for robotic welding. We propose to generate weld seams directly from a point cloud as opposed to using 3D models for offline planning of welding paths. For this application, we show a comparison between Harris 3D and our proposed approach on a panel workpiece.

Scripts provide rich textual annotation of movies, including dialogs, character names, and other situational descriptions. Exploiting such rich annotations requires aligning the sentences in the scripts with the corresponding video frames. Previous work on aligning movies with scripts predominantly relies on time-aligned closed-captions or subtitles, which are not always available. In this paper, we focus on automatically aligning faces in movies with their corresponding character names in scripts without requiring closed-captions/subtitles. We utilize the intuition that faces in a movie generally appear in the same sequential order as their names are mentioned in the script. We first apply standard techniques for face detection and tracking, and cluster similar face tracks together. Next, we apply a generative Hidden Markov Model (HMM) and a discriminative Latent Conditional Random Field (LCRF) to align the clusters of face tracks with the corresponding character names. Our alignment models (especially LCRF) significantly outperform the previous state-of-the-art on two different movie datasets and for a wide range of face clustering algorithms.

Linear direct feed drives are widely used in machine tools, but an abrupt counter force from the secondary part will induce the jerk to the metro frame contacted with the linear motor and cause the vibration of auxiliary devices on it. The jerk-decoupling cartridge (JDC) provides a buffer to reduce such an impact. To systematically take care of both the tracking error and the jerk induced to the metro frame, this paper presents an integrated design approach to determine parameters in the JDC and the position controller of the feed drive. The initial formulated non-convex optimization problem is converted to convex constrained gradient optimization problem and linear step searching problem. Thus, fast convergence of parameters is achieved within first few iterations. Through a series of simulation, the effectiveness of proposed methodology is verified.

Neural information recorded from electroencephalogram (EEG) provides new possibilities for diagnosis of brain abnormalities, cognitive monitoring, etc. However, many artifacts, such as eye blink and muscle movements, impact and contaminate EEG data. While traditional techniques proposed for artifact removal identified artifact on two-way data, (spatial x temporal), multidimensional nature of EEG data (spatial x temporal x spectral x condition x trial) is overlooked. In this work, we investigate the use of multiway analysis/tensor factorization on the extended EEG tensor (spatial x temporal x spectral), which is constructed from continuous wavelet transform, using Block Term Decomposition (BTD) of rank-(Lr, Lr, 1) for artifact removal. Eight different carefully designed experiments to study artifact typically produced by voluntarily, and sometimes involuntarily, behaviors using a subject were performed and analyzed. After the BTD decomposition, artifacted components are automatically identified removed using spatial and temporal features. The reconstructed signal from proposed method suppresses artifact while retains the signal texture of eight types of artifact investigated.

In the recent times, offshore activities are getting increasingly important, and marine vessels are prevalent in all the water bodies. This requires a detailed study of the effect of environmental forces of the marine structures. This paper aims at developing an unified framework to study the effect of wind force and moments on marine vessels. A neural network approach is developed to study the effect of longitudinal and side forces of wind, and the yaw moment. The study considers various types of marine vessels at different loading conditions, with a total of 22 marine vessels. Of these, 18 are used to train an ensemble of Extreme Learning Machine (ELM) neural network. The network thus developed is tested for generalization on 2 new type of vessels at 2 different loading conditions. Thus, the developed model is capable of predicting the wind force and moment coefficients, irrespective of the type of vessel used. An Ensemble of extreme learning machine, each with input parameters initialized at different regions of the input space, are trained with all training samples. For each sample, the ELM that produces the least mean square error is identified, and the output of that ELM is considered as the output for that sample. Thus, the randomness of the initialization in ELM is exploited to achieve superior generalization performance. Performance study to predict the wind force and moment coefficients of marine vessels show that the ensemble of ELM has superior prediction performance, compared to state of the art results for this problem.

Challenging multi-modal optimization problems have been very successfully solved by evolutionary computation (EC) techniques. To date, many methods have been proposed on evolutionary optimization for both single and multiobjective large scale problems. In the age of Big Data, there is an urge to take evolutionary optimization techniques to the next level for solving problems with even larger scales: thousands and millions of variables. These problems arise in many domains ranging from bioinformatics, to neuroscience and social simulations. In this paper, we investigate the use of EC to solve Big electroencephalography (EEG) data optimization problems with thousands of variables. The optimization problem attempts to identify maximum information that should be kept from a signal while minimizing the artifact. The high level of epistasis inherent in a signal can slow down the evolution. Therefore, we investigate the advantages of optimizing the problem in the frequency domain with different thresholds as opposed to the time domain. We propose synthetic EEG data sets of various scale and noise level. These data sets were the basis for the Optimization of Big Data 2015 Competition (BigOpt), CEC 2015. Two state-of-art multiobjective evolutionary algorithms (MOEAs) were evaluated. The results of this work suggest that frequency representation of the signals facilitates dimensionality reduction for big scale optimization of time series data, and hence provides faster and better quality solutions for EEG data cleaning. Moreover, the results suggest that existing state-of-art multiobjective evolutionary computation methods are extremely slow. Methods that can optimize the problem faster and with high quality are needed.

Many real-world optimization problems are subjected to uncertainties that may be characterized by the presence of noise in the objective functions. The estimation of distribution algorithm (EDA), which models the global distribution of the population for searching tasks, is one of the evolutionary computation techniques that deals with noisy information. This paper studies the potential of EDAs; particularly an EDA based on restricted Boltzmann machines that handles multi-objective optimization problems in a noisy environment. Noise is introduced to the objective functions in the form of a Gaussian distribution. In order to reduce the detrimental effect of noise, a likelihood correction feature is proposed to tune the marginal probability distribution of each decision variable. The EDA is subsequently hybridized with a particle swarm optimization algorithm in a discrete domain to improve its search ability. The effectiveness of the proposed algorithm is examined via eight benchmark instances with different characteristics and shapes of the Pareto optimal front. The scalability, hybridization, and computational time are rigorously studied. Comparative studies show that the proposed approach outperforms other state of the art algorithms.

Development of a 3-dimensional simulator for gyroscopically stabilized single wheel robot (gyrobot) is reported in this paper. This virtual environment of simulating 3D motion of the robot, under open-loop control and closed-loop control, can be used to expedite the design and optimization of the robot. Mechanical drawings of the gyrobot are first created using a CAD software, e.g., Solidworks and imported into the ADAMS, where the material type, density are defined. It is underscored using simulation results that the virtual prototype reflects the operation of the gyrobot. The 3D simulator has also been used to design and simulate a controller for autonomous operation of the gyrobot. Although this paper addresses the issues related to the gyrobot, the virtual environment can be easily used for design of other mechatronic systems including robots.

A very important aspect in developing human-robot interaction (HRI) is the ability to recognize people by sound source recognition. In this paper, we introduce an intelligent audio human detection system that is able to recognize user’s voice, and identified it from background sound. The sound sources recognition for human robot interaction is investigated using an unsupervised learning algorithm, neighborhood linear embedding (NLE), which is able to extract the intrinsic features such as neighborhood relationships, global distributions and clustering property of a given data set. Furthermore, motivated by the scale adaptivity of human’s perception, several scale invariant metrics are designed to enhance the intrinsic feature extraction performance of NLE. Simulations on different sound sources recognition are studied to demonstrate effective applications of the scale invariant NLE algorithm for robust sound recognition and identification to improve auditory system of robot for human robot interaction.

This paper proposes a new memetic evolutionary approach for rule extraction from datasets. The evolutionary algorithm integrated an adaptive micro-search intensity scheme inspired by artificial immune system (AIS) for local fine-tuning of the rules. In addition, the rules are encoded using variable length representation allowing easy adaptation. Through the structural mutation and crossover operators, the appropriate number of rules is optimized. Simulation results of the proposed method on real world benchmarking datasets demonstrated the effectiveness of the algorithm.

Binary representation suffers from the problem of positional dependence, where the amplitude of phenotype variation is dependent on the position of the altered genotype bits. However, this is contrary to conventional variation operations that treat each genotype bit equally. Positional dependence can be attributed to the poor locality, which results in neighboring genotypes having low correlation in the phenotype space, reducing the effectiveness of systematic local search and evolutionary search based on small mutation steps. For this purpose, this paper will propose an alternative genotype-phenotype mapping for binary representation that introduces redundancy into the mapping and removes the exponential orderings between the alleles, hence improving the locality between the genotype and phenotype search space. Empirical study conducted based on distribution, locality, and mutation innovation revealed key algorithmic characteristics of the proposed code, and its practicality is validated by comparative studies based on different benchmark optimization problems. Possible approaches to resolve the overrepresentation problem due to redundancy will be suggested, exhibiting its flexibility and variability in implementation.

This paper proposes a new multi-objective evolutionary approach for training recurrent neural networks (RNNs). The algorithm uses features of a variable length representation allowing easy adaptation of neural networks structures and a micro genetic algorithm (muGA) with an adaptive local search intensity scheme for local fine-tuning. In addition, a structural mutation (SM) operator for evolving the appropriate number of neurons for RNNs is used. Simulation results demonstrated the effectiveness of proposed method for system identification tasks.

This paper aims to address a more realistic model of the portfolio optimization problem, unlike other previous evolutionary multiobjective optimization approaches. For this purpose, an order-based representation is proposed, which can be easily extended to handle various realistic constraints like floor and ceiling constraint and cardinality constraint. Furthermore, the current experimental platform for evolutionary multiobjective portfolio optimization will be improved by introducing diversity measures and statistical analysis that are commonly used in performance assessment of multiobjective optimizers. Comparative study with other conventional representations, based on benchmark problems obtained from the OR-library, demonstrated that the proposed representation is able to attain a better approximation of the efficient frontier in terms of proximity and diversity. Experimental results also validated its viability and practicality in handling the various realistic constraints. Lastly, preference based techniques are considered also, allowing the evolutionary search to be focused on specific region of the efficient frontier. Future work includes improving the algorithmic model with more sophisticated variation operators and local search operators for better exploration and exploitation of the search space.

This paper studies a hierarchical approach for incrementally driving a nonholonomic mobile robot to its destination in unknown environments. The A* algorithm is modified to handle a map containing unknown information. Based on it, optimal (discrete) paths are incrementally generated with a periodically updated map. Next, accelerations in varying velocities are taken into account in predicting the robot pose and the robot trajectory resulting from a motion command. Obstacle constraints are transformed to suitable velocity limits so that the robot can move as fast as possible while avoiding collisions when needed. Then, to trace the discrete path, the system searches for a waypoint-directed optimized motion in a reduced 1-D translation or rotation velocity space. Various situations of navigation are dealt with by using different strategies rather than a single objective function. Extensive simulations and experiments verified the efficacy of the proposed approach.

This paper proposes a practical method for planning paths incrementally for mobile robots in unknown environments using the latest sensory information. A* algorithm was modified in this research for it to be able to handle an occupancy grid map with unknown information. Then the paper presented an algorithm that is able to robustly and incrementally searching for an optimal path based on the partial map simultaneously built by the robot. Waypoints was generated to further optimize the obtained path and were sequentially traced by the robot in a simple, reactive way. Extensive simulations and experiments were carried out to verify the proposed planning algorithm

In this paper, an Instant Goal approach is proposed for collision-free boundary following of obstacles of arbitrary shape and globally convergent path planning in unknown environments. Firstly, for effective knowledge representation and manipulation, a vector representation is presented, which not only saves much space but also conforms to the physical properties of range sensors. Secondly, the concept of Instant Goals is introduced enabling the robot to perform boundary following in a "natural" human-like manner, with additional measures taken to ensure that the robot is moving "forward" along the boundary, even if the obstacle is of arbitrary shape and disturbing obstacles are present. Collision checking is performed simultaneously and, when needed, collision avoidance is efficiently incorporated in. Based on the approach of boundary following, a realistic sensor-based path planner with global convergence property is designed for the robot capable of acquiring discrete and noisy range data. Realistic simulation experiments validate the effectiveness of the proposed approaches.