Open Dynamics Engine を用いたスノーボードロボットシミュレータの開発

IEEE International Conference on Robotics and Automation (ICRA) におけるフルードパワー技術の研究動向

Robotic technologies, whether they are remotely operated vehicles, autonomous agents, assistive devices, or novel control interfaces, offer many promising capabilities for deployment in real world environments. Post-disaster scenarios are a particularly relevant target for applying such technologies, due to the challenging conditions faced by rescue workers and the possibility to increase their efficacy while decreasing the risks they face. However, fielddeployable technologies for rescue work have requirements for robustness, speed, versatility, and ease of use that may not be matched by the state of the art in robotics research. This paper aims to survey the current state of the art in ground and aerial robots, marine and amphibious systems, and human-robot control interfaces and assess the readiness of these technologies with respect to the needs of first responders and disaster recovery efforts. We have gathered expert opinions from emergency response stakeholders and researchers who conduct field deployments with them in order to understand these needs, and we present this assessment as a way to guide future research toward technologies that will make an impact in real world disaster response and recovery.

/pdf/the-current-state-and-future-outlook-of-rescue-robotics-19pbfgwbpw.pdf

The current state and future outlook of rescue robotics

A Global Navigation Satellite System (GNSS)/Inertial Navigation System (INS)/Light Detection and Ranging (LiDAR)-Simultaneous Localization and Mapping (SLAM) integrated navigation system based on graph optimization is proposed and implemented in this paper. The navigation results are obtained by the information fusion of the GNSS position, Inertial Measurement Unit (IMU) preintegration result and the relative pose from the 3D probability map matching with graph optimizing. The sliding window method was adopted to ensure that the computational load of the graph optimization does not increase with time. Land vehicle tests were conducted, and the results show that the proposed GNSS/INS/LiDAR-SLAM integrated navigation system can effectively improve the navigation positioning accuracy compared to GNSS/INS and other current GNSS/INS/LiDAR methods. During the simulation of one-minute periods of GNSS outages, compared to the GNSS/INS integrated navigation system, the root mean square (RMS) of the position errors in the North and East directions of the proposed navigation system are reduced by approximately 82.2% and 79.6%, respectively, and the position error in the vertical direction and attitude errors are equivalent. Compared to the benchmark method of GNSS/INS/LiDAR-Google Cartographer, the RMS of the position errors in the North, East and vertical directions decrease by approximately 66.2%, 63.1% and 75.1%, respectively, and the RMS of the roll, pitch and yaw errors are reduced by approximately 89.5%, 92.9% and 88.5%, respectively. Furthermore, the relative position error during the GNSS outage periods is reduced to 0.26% of the travel distance for the proposed method. Therefore, the GNSS/INS/LiDAR-SLAM integrated navigation system proposed in this paper can effectively fuse the information of GNSS, IMU and LiDAR and can significantly mitigate the navigation error, especially for cases of GNSS signal attenuation or interruption.

GNSS/INS/LiDAR-SLAM Integrated Navigation System Based on Graph Optimization

In this paper, we proposed a multi-sensor integrated navigation system composed of GNSS (global navigation satellite system), IMU (inertial measurement unit), odometer (ODO), and LiDAR (light detection and ranging)-SLAM (simultaneous localization and mapping). The dead reckoning results were obtained using IMU/ODO in the front-end. The graph optimization was used to fuse the GNSS position, IMU/ODO pre-integration results, and the relative position and relative attitude from LiDAR-SLAM to obtain the final navigation results in the back-end. The odometer information is introduced in the pre-integration algorithm to mitigate the large drift rate of the IMU. The sliding window method was also adopted to avoid the increasing parameter numbers of the graph optimization. Land vehicle tests were conducted in both open-sky areas and tunnel cases. The tests showed that the proposed navigation system can effectually improve accuracy and robustness of navigation. During the navigation drift evaluation of the mimic two-minute GNSS outages, compared to the conventional GNSS/INS (inertial navigation system)/ODO integration, the root mean square (RMS) of the maximum position drift errors during outages in the proposed navigation system were reduced by 62.8%, 72.3%, and 52.1%, along the north, east, and height, respectively. Moreover, the yaw error was reduced by 62.1%. Furthermore, compared to the GNSS/IMU/LiDAR-SLAM integration navigation system, the assistance of the odometer and non-holonomic constraint reduced vertical error by 72.3%. The test in the real tunnel case shows that in weak environmental feature areas where the LiDAR-SLAM can barely work, the assistance of the odometer in the pre-integration is critical and can effectually reduce the positioning drift along the forward direction and maintain the SLAM in the short-term. Therefore, the proposed GNSS/IMU/ODO/LiDAR-SLAM integrated navigation system can effectually fuse the information from multiple sources to maintain the SLAM process and significantly mitigate navigation error, especially in harsh areas where the GNSS signal is severely degraded and environmental features are insufficient for LiDAR-SLAM.

GNSS/IMU/ODO/LiDAR-SLAM Integrated Navigation System Using IMU/ODO Pre-Integration

The objective of this study was to achieve simultaneous localization and mapping (SLAM) of firefighter robots for petrochemical complexes. Consistency of the SLAM map is important because human operators compare the map with aerial images and identify target positions on the map. The global positioning system (GPS) enables increased consistency. Therefore, this paper describes two Rao-Blackwellized particle filters (RBPFs) based on GPS and light detection and ranging (LIDAR) as SLAM solutions. Fast-SLAM 1.0 and Fast-SLAM 2.0 were used in grid maps for RBPFs in this study. We herein propose the use of Fast-SLAM to combine GPS and LIDAR. The difference between the original Fast-SLAM and the proposed method is the use of the log-likelihood function of GPS; the proposed combination method is implemented using a probabilistic mathematics formulation. The proposed methods were evaluated using sensor data measured in a real petrochemical complex in Japan ranging in size from 550–380 m. RTK-GPS data was used for the GPS measurement and had an availability of 56%. Our results showed that Fast-SLAM 2.0 based on GPS and LIDAR in a dense grid map produced the best results. There was significant improvement in alignment to aerial data, and the mean square root error was 0.65 m. To evaluate the mapping consistency, accurate 3D point cloud data measured by Faro Focus 3D (± 3 mm) was used as the ground truth. Building sizes were compared; the minimum mean errors were 0.17 and 0.08 m for the oil refinery and management building area and the area of a sparse building layout with large oil tanks, respectively. Consequently, a consistent map, which was also consistent with an aerial map (from Google Maps), was built by Fast-SLAM 1.0 and 2.0 based on GPS and LIDAR. Our method reproduced map consistency results for ten runs with a variance of ± 0.3 m. Our method reproduced map consistency results with a global accuracy of 0.52 m in a low RTK-Fix-GPS environment, which was a factory with a building layout similar to petrochemical complexes with 20.9% of RTK-Fix-GPS data availability.

/pdf/consistent-map-building-in-petrochemical-complexes-for-3q8m6b2480.pdf

Consistent map building in petrochemical complexes for firefighter robots using SLAM based on GPS and LIDAR

Perception is the main key in enabling robots to react to and interact with their environment. Particularly, for multi-floor operations, the robot must robustly detect and localize stairs to allow for safe climbing. In this paper, we develop a graph-based stairway detection method for point cloud data, that can detect a large variety of stairways. Our approach first segments planar regions and extracts the stair tread- and stair riser-shaped segments. With these segments, a dynamic graph model is initialized that is used to detect stairs including the railing system in the surroundings. We show that our system can accurately detect and localize different stairways from a variety of different positions, including descending stairs. Our system's accuracy is higher than those of most state-of-the-art stairway detection methods even in case of sparse point cloud data.

3D graph based stairway detection and localization for mobile robots

One of the major challenges for mobile robots in human-shaped environments is navigating stairways. This study presents a method for accurately detecting, localizing, and estimating the characteris...

Robust stairway-detection and localization method for mobile robots using a graph-based model and competing initializations

The Kumamoto Earthquake occurred in April 2016. We conducted an investigation using the active scope camera to examine the interiors of the collapsed houses. The robot video scope can move by itself to probe narrow gaps. We could safely gather information by inserting it inside houses. We further considered the future possible improvements to the robot based on the investigation. We also determined the constraints to be considered for the robot operation in disaster areas. In addition, we created a test field imitating the features of collapsed houses. We used this field to evaluate our robot mobility and related technologies that are being developed for future applications.

Use of active scope camera in the Kumamoto Earthquake to investigate collapsed houses

Current self-driving vehicles rely on detailed maps of the environment, that contains exhaustive semantic information. This work presents a strategy to utilize the recent advancements in semantic segmentation of images, fuse the information extracted from the camera stream with accurate depth measurements of a Lidar sensor in order to create large scale semantic labeled point clouds of the environment. We fuse the color and semantic data gathered from a round-view camera system with the depth data gathered from a Lidar sensor. In our framework, each Lidar scan point is projected onto the camera stream to extract the color and semantic information while at the same time a large scale 3D map of the environment is generated by a Lidar-based SLAM algorithm. While we employed a network that achieved state of the art semantic segmentation results on the Cityscape dataset [1] (IoU score of 82.1%), the sole use of the extracted semantic information only achieved an IoU score of 38.9% on 105 manually labeled 5x5m tiles from 5 different trial runs within the Sendai city in Japan (this decrease in accuracy will discussed in section III-B). To increase the performance, we reclassify the label of each point. For this two different approaches were investigated: a random forest and SparseConvNet [2] (a deep learning approach). We investigated for both methods how the inclusion of semantic labels from the camera stream affected the classification task of the 3D point cloud. To which end we show, that a significant performance increase can be achieved by doing so - 25.4 percent points for random forest (40.0% w/o labels to 65.4% with labels) and 16.6 in case of the SparseConvNet (33.4% w/o labels to 50.8% with labels). Finally, we present practical examples on how semantic enriched maps can be employed for further tasks. In particular, we show how different classes (i.e. cars and vegetation) can be removed from the point cloud in order to increase the visibility of other classes (i.e. road and buildings). And how the data could be used for extracting the trajectories of vehicles and pedestrians.

Shotaro Kojima

Papers

Consistent map building in petrochemical complexes for firefighter robots using SLAM based on GPS and LIDAR

3D graph based stairway detection and localization for mobile robots

Robust stairway-detection and localization method for mobile robots using a graph-based model and competing initializations

Use of active scope camera in the Kumamoto Earthquake to investigate collapsed houses

Fusion of Camera and Lidar Data for Large Scale Semantic Mapping