透過您的圖書館登入
IP:44.220.41.140
  • 學位論文

採樣式路徑規劃與立體即時建圖及定位於具社交感知之服務型機器人應用

Sampling-based Motion Planning with 3D Simultaneous Localization and Mapping for Social Aware Service Robotics Applications

指導教授 : 羅仁權

摘要


在這份研究中,介紹了為室內服務型機器人打造的自主導航框架方案與一套路徑規劃演算法。 本研究皆實做於機器人作業系統(ROS)上。ROS 是面向機器人的後設操作系統(meta-operating system)。它能夠提供類似操作系統的諸多功能, 如硬體抽象、底層設備控制、常用功能實現、進程間訊息傳遞和程序包管理等。此外,它還提供相關工具和程式庫,用於獲取、編譯、編輯代碼以及多個計算機之間運行程序完成分布式計算。 本研究實作的框架包含了分層路徑規劃、Costmap 更新、建圖與定位、以及 底層驅動控制等集成可行的導航系統。社交感知透過機器人本身的雷射以及顏色 深度感測器所測得的資訊建立動態 Costmap ,以感知空間中的人、物及機器人三 者的關係。隨著在高度動態空間中移動的需求逐漸增高,機器人須具備更高度 敏捷與靈活的路徑規劃與動態追蹤演算法,以確保安全的人機互動。為此,在這份研究中,我們提出一種新的採樣規劃演算法,融合了搜尋規劃類演算法的 Anytime Dynamic 特點以及採樣規劃演算法簡潔運算架構的特點。我們藉由模擬 環境、實體部分探索環境、以及完全探索實體環境進行實驗, 將本研究提出的演算 法與當前主要搜尋式及採樣式路徑規劃演算法作比較。我們提出的演算法在單次遞迴所耗路徑規劃代價不僅低於一般 RRT 和 RRT* 達 8.5% 至 16.7% , 而所需運算 時間卻比 RRT 低58.17%以及 RRT* 的 95%. 這在不規則區域導航的來說, 已經符合 動態規劃得要求。 實驗證明此路徑規劃演算法能獲得更快且產生路徑規劃成本更 低的軌跡,同時層狀 costmap 也能有效的更新,避免移動中的碰撞與有效迴避動 靜態障礙物及機器人周遭的人。在社交感知方面,我們以高斯分布代表偵測到的 人之座標,以此建立一個人際距離的數學模型,隨著人際距離的改變,具社交感知的導航系統能尊重他人的私人空間並在社交規範下行動,在人機互動走入真實社會的前提下至關重要。除此之外,這項研究更可被延伸至人機互動、多機器人 探索,或者物聯網與機器人學的整合等相關領域。

並列摘要


In the present work, an socially aware autonomous navigation framework and motion planning algorithm for indoor service robot are proposed. The entirety of our work is based on Robot Operating System (ROS), which serves as the Linux-based middle-ware on which all robotics applications execute and communicate with each other based on an unified formats of messages, and allows sharing of information within a cluster of devices. Within ROS, our navigational framework consists of integrating layered planning scheme, layered costmap update (a ROS concept based on [2]), mapping and localization, as well as base control into a viable navigation system. The social aware functionality is implemented via an establishment of dynamic costmap registering the proxemics of each perceived individual by the robot’s onboard Laser Scan as well as RGB-D sensors. With the aid of sensorial fusion perception of humans within highly dynamic configuration space poses high demand for more agile and flexible motion planning algorithms as well as faster people tracking techniques to ensure safer interaction. For such purpose, this work presents a novel biased sampling-based planning approach which displays both the Anytime Dynamic planning characteristics of search-based path planning algorithms with the computational simplicity of single-query sampling-based approach. We evaluate our motion planning algorithm with 3 major benchmarks: one simulated environment and two real-world scenarios involving partially explored and fully explored maps of the same maze-like indoor space. We compare our proposed algorithm ADRRT* with several major search-based and sampling-based algorithms in terms of the spent cost and computation time on each iteration. And on average, our algorithm not only consumes cost which ranges 8.5% to 16.7% less than its counterparts, but also occupies les than comvi pared to as much as 58.17% to RRT and 95% to RRT* in non-convex environement such as Room 302 of our laboratory. While our technique proves to yield faster and less costly trajectories, the layered costmaps should also be effectively updated to ensure the collision avoidance both with static obstacles as well as people at the robot’s surroundings on a real-time basis. The dynamic costmap layers registers the perceived people’s poses in terms of Gaussian pose estimate, representing the proxemics of each individual. With the notion of proxemics, the navigation framework respects the personal space of others and maneuver according to social norms, an important feature to regulate robotic behavior in order to integrate robots into our society. Such study also serves as springboard toward future works related not limited to human-robot-interaction, multi-robot exploration, and further integration of robotics with the Internet of Things (IoT) framework.

參考文獻


[55] 吳謝浩 et al., “基於圖優化同時定位地構建與移動物體追蹤功能之多感測器融合行動機人,” 2014.
[17] Benjamin Kuipers and Yung-Tai Byun, “A robust, qualitative method for robot spa- tial learning.,” in AAAI, 1988, vol. 88, pp. 774–779.
[73] Dave Ferguson and Anthony Stentz, “Anytime, dynamic planning in high- dimensional search spaces,” in Robotics and Automation, 2007 IEEE International Conference on. IEEE, 2007, pp. 1310–1315.
[37] Renato Salas-Moreno, Richard Newcombe, Hauke Strasdat, Paul Kelly, and Andrew Davison, “Slam++: Simultaneous localisation and mapping at the level of objects,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recogni- tion, 2013, pp. 1352–1359.
[5] Mohammad Naim Rastgoo, Bahareh Nakisa, Mohammad Faidzul Nasrudin, AH- MAD NAZRI, and MOHD ZAKREE, “A critical evaluation of literature on robot path planning in dynamic environment.,” Journal of Theoretical & Applied Infor- mation Technology, vol. 70, no. 1, 2014.

延伸閱讀