Transformable semantic map based navigation using autonomous deep learning object segmentation

Furuta, Yoshihiro; Wada, Kazumi; Murooka, Masaki; Nozawa, Satoshi; Kakiuchi, Yohei; Okada, Kei; Inaba, Masayuki

doi:10.1109/humanoids.2016.7803338

Cited by 10 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gait Stability Navigation Automatic learning [42], [43], [50] [65], [78] [44], [51], [52], [53], [54], [55], [62], [64], [66], [69], [70], [71], [68], [75] [47], [49], [59], [60], [61], [77] [45], [56], [57], [58], [63], [67] [72], [73], [79], [80], [81], [82], [83], [84], [85], [86], [87], [88]…”

Section: Papermentioning

confidence: 99%

“…Paper Percentage (%) HRP-2 [45], [63], [66], [80] 9.52 % Amber [42] 2.38 % Nao [42], [44], [52], [62], [64], [69], [70], [75] As it can be observed, the Lola and Nao robot are the most used in the investigations, with respect to the Lola robot, its great use is due to the fact that there are multiple works belonging to the same authors, and they have followed it up to improve it through the years. While the use of the Nao robot is due to the fact that it is a robot with last generation technology, it has a high degree of interactivity for any type of user; it is fully programmable, and currently more than 400 universities are working on this platform.…”

Section: Robotmentioning

confidence: 99%

See 1 more Smart Citation

Towards the Development of a Navigation System for a Bipedal Robot: Preliminary Analysis of the Literature

Ortega-Palacios¹,

Guerrero-García²,

González-Calleros³

2019

RCS

View full text Add to dashboard Cite

In the literature, several works are reported about the gait of bipedal robots. Some papers are associated with stability or automatic learning and navigation, but no paper was found that includes the variables of bipedal gait, stability, navigation and automatic learning, all applied in an indoor bipedal robot. Our objective is, after the analysis of the state of the art, to propose a methodology that will allow the autonomous navigation of a bipedal robot and validate its degree of autonomy with respect to the evaluation metrics reported in the literature.

show abstract

Section: Papermentioning

confidence: 99%

Section: Robotmentioning

confidence: 99%

Towards the Development of a Navigation System for a Bipedal Robot: Preliminary Analysis of the Literature

Ortega-Palacios¹,

Guerrero-García²,

González-Calleros³

2019

RCS

View full text Add to dashboard Cite

show abstract

“…Zhu et al [24] proposed a target-driven visual navigation method using a reinforcement learning model that generalizes across targets and scenes. Furuta et al [25] proposed semantic map based navigation which consisted of generating a deep learning enabled semantic map from annotated world and object based navigation using learned semantic map representation. Most approaches mentioned above have two main problems:…”

Section: Related Workmentioning

confidence: 99%

Visual Semantic Navigation Based on Deep Learning for Indoor Mobile Robots

Wang

Zhao

Huo³

et al. 2018

Complexity

View full text Add to dashboard Cite

In order to improve the environmental perception ability of mobile robots during semantic navigation, a three-layer perception framework based on transfer learning is proposed, including a place recognition model, a rotation region recognition model, and a “side” recognition model. The first model is used to recognize different regions in rooms and corridors, the second one is used to determine where the robot should be rotated, and the third one is used to decide the walking side of corridors or aisles in the room. Furthermore, the “side” recognition model can also correct the motion of robots in real time, according to which accurate arrival to the specific target is guaranteed. Moreover, semantic navigation is accomplished using only one sensor (a camera). Several experiments are conducted in a real indoor environment, demonstrating the effectiveness and robustness of the proposed perception framework.

show abstract

“…There are several advantages to the combination of these two technologies. First of all, the inclusion of semantic information within an environmental map provides a much greater range of functionality for autonomous vehicles than geometry alone [ 4 ]. For example, the semantic information in the map allows the autonomous vehicles to know what objects are around them even when the sensors cannot detect the objects, which give a cue for the drivable region.…”

Section: Introductionmentioning

confidence: 99%

Semantic Point Cloud Mapping of LiDAR Based on Probabilistic Uncertainty Modeling for Autonomous Driving

Cho

Kim

Park

et al. 2020

Sensors

View full text Add to dashboard Cite

LiDAR-based Simultaneous Localization And Mapping (SLAM), which provides environmental information for autonomous vehicles by map building, is a major challenge for autonomous driving. In addition, the semantic information has been used for the LiDAR-based SLAM with the advent of deep neural network-based semantic segmentation algorithms. The semantic segmented point clouds provide a much greater range of functionality for autonomous vehicles than geometry alone, which can play an important role in the mapping step. However, due to the uncertainty of the semantic segmentation algorithms, the semantic segmented point clouds have limitations in being directly used for SLAM. In order to solve the limitations, this paper proposes a semantic segmentation-based LiDAR SLAM system considering the uncertainty of the semantic segmentation algorithms. The uncertainty is explicitly modeled by proposed probability models which are come from the data-driven approaches. Based on the probability models, this paper proposes semantic registration which calculates the transformation relationship of consecutive point clouds using semantic information with proposed probability models. Furthermore, the proposed probability models are used to determine the semantic class of the points when the multiple scans indicate different classes due to the uncertainty. The proposed framework is verified and evaluated by the KITTI dataset and outdoor environments. The experiment results show that the proposed semantic mapping framework reduces the errors of the mapping poses and eliminates the ambiguity of the semantic information of the generated semantic map.

show abstract

Transformable semantic map based navigation using autonomous deep learning object segmentation

Cited by 10 publications

References 15 publications

Towards the Development of a Navigation System for a Bipedal Robot: Preliminary Analysis of the Literature

Towards the Development of a Navigation System for a Bipedal Robot: Preliminary Analysis of the Literature

Visual Semantic Navigation Based on Deep Learning for Indoor Mobile Robots

Semantic Point Cloud Mapping of LiDAR Based on Probabilistic Uncertainty Modeling for Autonomous Driving

Contact Info

Product

Resources

About