Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li, Deguo Xia, Jizhou Huang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Autonomous exploration in unknown environments is a crucial challenge for various applications of unmanned aerial vehicles (UAVs). However, in large-scale scenarios, existing methods suffer from inefficient environmental information acquisition, computationally expensive exploration planning, and inconsistent motion. In this work, we present a novel method for rapid UAV autonomous exploration in large-scale environments. We develop a surface frontier guided viewpoints generation strategy that supports efficient coverage of scenario. Besides, we introduce an incremental viewpoint clustering method to approximate distant viewpoints using fewer anchor points, decreasing the computational costs of exploration tour planning. Building upon this, we propose a history-informed tour planning method that incorporates information from previous tour into the optimization process, maintaining motion consistency. Extensive simulation experiments validate that our method outperforms existing state-of-the-art methods in terms of exploration time, travel distance, and run time. Various real-world experiments are conducted to indicate the practicality of our approach. The source code will be released to benefit the community1.

Source code refactoring brings many benefits to the software being developed, e.g., reduces the likelihood of future development failures and simplifies the implementation of new features. Among the various code refactoring activities, identifier renaming is one of the most frequent software development activities conducted by developers, which plays an important role in program analysis and understanding. However, manually detecting identifier renaming opportunities is time-consuming and labor-intensive. Recently, researchers have proposed several automatic renaming opportunity identification approaches for identifiers. However, existing approaches only focus on one or several specific types of identifiers without generally considering all the types of identifiers. To resolve this problem, we put forward a new approach to detect identifier renaming opportunities by fully exploiting the changes of the programming context and the related code entities. Specifically, we first utilize a siamese network, which employs different attention headers to incorporate the programming context and the related code entities, to derive the semantically meaningful embeddings of identifiers. We then utilize these vectors to train a classifier, which can be used for predicting renaming opportunities for identifiers. Experimental results on 29 255 identifiers from ten Java projects in the Apache community demonstrate that our approach outperforms the state-of-the-art baseline approach by 11.97% as for the average F-Measure in identifying renaming opportunities for all the types of identifiers. In addition, we also verified the effectiveness of some key components of our approach. For instance, utilizing the related code entities into our approach improves the average F-Measure by 6.60%.

Identifiers play an important role in helping developers analyze and comprehend source code. However, many identifiers exist that are inconsistent with the corresponding code conventions or semantic functions, leading to flawed identifiers. Hence, identifiers need to be renamed regularly. Even though researchers have proposed several approaches to identify identifiers that need renaming and further suggest correct identifiers for them, these approaches only focus on a single or a limited number of granularities of identifiers without universally considering all the granularities and suggest a series of sub-tokens for composing identifiers without completely generating new identifiers. In this article, we propose a novel identifier renaming prediction and suggestion approach. Specifically, given a set of training source code, we first extract all the identifiers in multiple granularities. Then, we design and extract five groups of features from identifiers to capture inherent properties of identifiers themselves and the relationships between identifiers and code conventions, as well as other related code entities, enclosing files, and change history. By parsing the change history of identifiers, we can figure out whether specific identifiers have been renamed or not. These identifier features and their renaming history are used to train a Random Forest classifier, which can be further used to predict whether a given new identifier needs to be renamed or not. Subsequently, for the identifiers that need renaming, we extract all the related code entities and their renaming change history. Based on the intuition that identifiers are co-evolved as their relevant code entities with similar patterns and renaming sequences, we could suggest and recommend a series of new identifiers for those identifiers. We conduct extensive experiments to validate our approach in both the Java projects and the Android projects. Experimental results demonstrate that our approach could identify identifiers that need renaming with an average F-measure of more than 89%, which outperforms the state-of-the-art approach by 8.30% in the Java projects and 21.38% in the Android projects. In addition, our approach achieves a Hit@10 of 48.58% and 40.97% in the Java and Android projects in suggesting correct identifiers and outperforms the state-of-the-art approach by 29.62% and 15.75%, respectively.

Yongwei Zhou, Junwei Bao, Chaoqun Duan, Haipeng Sun, Jiahui Liang, Yifan Wang, Jing Zhao, Youzheng Wu, Xiaodong He, Tiejun Zhao. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Information Retrieval (IR) techniques have been widely utilized by a growing number of software maintenance activities. However, there is a mismatch between source code lexicon (especially identifiers) and vocabulary in software artifacts, leading to the inefficiency of IR techniques. Consequently, it is essential to normalize identifiers, whose aim is to parse identifiers into several natural language terms. Identifier splitting significantly impacts on the effectiveness of identifier normalization. Even though researchers have proposed several approaches to split identifiers, three main drawbacks remain to be resolved, including without considering morphemes, over-splitting, and under-splitting. In this paper, we propose a new Character-level Hybrid-granularity Identifier Splitting approach CHIS to resolve the three drawbacks and better split identifiers. CHIS combines the Bidirectional Encoder Representation from Transformers (BERT) and Conditional Random Fields (CRF) to train a deep learning model to split identifiers. In addition, CHIS further employs a pre-processing component and a post-processing component to resolve the morpheme acquisition drawback and the over-splitting as well as the under-splitting drawbacks respectively, thus further improving its performance. Specifically, in the pre-processing component, CHIS obtains and labels the most frequent subwords of the training identifiers as morphemes through the Byte Pair Encoding (BPE) algorithm and the sequence labeling algorithm. In the post-processing component, CHIS iteratively merges and splits the splitting results obtained by the deep learning model to resolve the over-splitting and under-splitting drawbacks. We conduct extensive experiments to show the effectiveness of CHIS. Experimental results show that CHIS achieves the Accuracy of 0.943 on average and outperforms the state-of-the-art approach by 0.085 on average. In addition, the effectiveness of the pre-processing and post-processing components of CHIS are also validated.

During the process of software development and maintenance, developers would regularly refactor existing source code to improve efficiency and maintainability. Among various code refactoring activities, method renaming often happens within the whole project evolution process. To perform method renaming, developers should first identify the exact methods that should be renamed, which is generally tedious and error-prone through manual analysis. Towards this end, researchers have proposed some approaches to automatically recommend candidate methods for renaming. To further improve the performance of existing techniques, in this paper, we propose a novel approach that fully leverages historical code changes and overlapping relationships among code entities to identify renaming opportunities for methods. Specifically, we first embed methods into vectors and incorporate overlapping relationships among code entities by using different attention heads in a deep learning network. Then, we apply these obtained vectors to train a classifier to predict potential renaming opportunities for methods. Finally, we utilize historical renaming activities of related code entities to further refine the predicted results. Experimental results on 114,398 methods from 10 open source Java projects show that our approach could outperform the state-of-the-art approach by achieving an average F-measure of 80.02%. To better validate the effectiveness of our approach, we also explore the performance of some major components of our approach. For example, we find that employing related code entities help to improve the performance of our approach by 40.40% in terms of the average F-measure.

Robotic endoscopes have the potential to help endoscopists position tools during procedures, to propel the endoscope to the desired position, to automate functions and to prevent perforations during procedures. This paper outlines the modular architecture for a continuum robotic endoscope with multiple bending segments along the length of the endoscope. Each of the segments is modular, containing a set of actuation motors that drive short cables in the continuum segments. Each modular segment of the robot is 15 mm in diameter, can turn 180 degrees and has a turning speed ranging from 35 to 250 degrees per second. The robot is composed of seven of these modular segments, has 14 degrees of freedom, is 0.91 m long and has a mass of 157 grams. The implementation for the mechanical, electrical, and software design is described and the robotic endoscope bending motions are sensed, simulated and controlled using kinematic models. Lastly, path planning trajectories of the endoscope segments are designed and coordinated to help propel the robot forward in an uncoiling motion and in a follow-the-leader fashion along a path that emulates simplified turns in a colon. We show that the robotic endoscope is able to exert less force on the walls of the colon emulation path, enable automated insertion into the patient, and execute colon wall avoidance and linear scanning motions not available in conventional endoscopes.