Pub Date : 2022-11-11DOI: 10.1109/IRC55401.2022.00081
Joshua Springer
Landing is a challenging part of autonomous drone flight and a great research opportunity. This PhD proposes to improve on fiducial autonomous landing algorithms by making them more flexible. Further, it leverages its location, Iceland, to develop a method for landing on lava flows in cooperation with analog Mars exploration missions taking place in Iceland now – and potentially for future Mars landings.
{"title":"Autonomous Multirotor Landing on Landing Pads and Lava Flows","authors":"Joshua Springer","doi":"10.1109/IRC55401.2022.00081","DOIUrl":"https://doi.org/10.1109/IRC55401.2022.00081","url":null,"abstract":"Landing is a challenging part of autonomous drone flight and a great research opportunity. This PhD proposes to improve on fiducial autonomous landing algorithms by making them more flexible. Further, it leverages its location, Iceland, to develop a method for landing on lava flows in cooperation with analog Mars exploration missions taking place in Iceland now – and potentially for future Mars landings.","PeriodicalId":282759,"journal":{"name":"2022 Sixth IEEE International Conference on Robotic Computing (IRC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129754561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-19DOI: 10.1109/IRC55401.2022.00058
Francisco Roldan Sanchez, Stephen Redmond, Kevin McGuinness, Noel E. O'Connor
Robotic manipulation and control has increased in importance in recent years. However, state of the art techniques still have limitations when required to operate in real world applications. This paper explores Hindsight Experience Replay both in simulated and real environments, highlighting its weaknesses and proposing reinforcement-learning based alternatives based on reward and goal shaping. Additionally, several research questions are identified along with potential research directions that could be explored to tackle those questions.
{"title":"Towards advanced robotic manipulation","authors":"Francisco Roldan Sanchez, Stephen Redmond, Kevin McGuinness, Noel E. O'Connor","doi":"10.1109/IRC55401.2022.00058","DOIUrl":"https://doi.org/10.1109/IRC55401.2022.00058","url":null,"abstract":"Robotic manipulation and control has increased in importance in recent years. However, state of the art techniques still have limitations when required to operate in real world applications. This paper explores Hindsight Experience Replay both in simulated and real environments, highlighting its weaknesses and proposing reinforcement-learning based alternatives based on reward and goal shaping. Additionally, several research questions are identified along with potential research directions that could be explored to tackle those questions.","PeriodicalId":282759,"journal":{"name":"2022 Sixth IEEE International Conference on Robotic Computing (IRC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126571177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-26DOI: 10.1109/IRC55401.2022.00042
Sahar Salimpour, J. P. Queralta, Tomi Westerlund
Automatic detection of visual anomalies and changes in the environment has been a topic of recurrent attention in the fields of machine learning and computer vision over the past decades. A visual anomaly or change detection algorithm identifies regions of an image that differ from a reference image or dataset. The majority of existing approaches focus on anomaly or fault detection in a specific class of images or environments, while general-purpose visual anomaly detection algorithms are more scarce in the literature. In this paper, we propose a comprehensive deep learning framework for detecting anomalies and changes in a priori unknown environments after a reference dataset is gathered, and without need for retraining the model. We use the SuperPoint and SuperGlue feature extraction and matching methods to detect anomalies based on reference images taken from a similar location and with partial overlapping of the field of view. We also introduce a self-calibrating method for the proposed model in order to address the problem of sensitivity to feature matching thresholds and environmental conditions. To evaluate the proposed framework, we have used a ground robot system for the purpose of reference and query data collection. We show that high accuracy can be obtained using the proposed method. We also show that the calibration process enhances changes and foreign object detection performance.
{"title":"Self-Calibrating Anomaly and Change Detection for Autonomous Inspection Robots","authors":"Sahar Salimpour, J. P. Queralta, Tomi Westerlund","doi":"10.1109/IRC55401.2022.00042","DOIUrl":"https://doi.org/10.1109/IRC55401.2022.00042","url":null,"abstract":"Automatic detection of visual anomalies and changes in the environment has been a topic of recurrent attention in the fields of machine learning and computer vision over the past decades. A visual anomaly or change detection algorithm identifies regions of an image that differ from a reference image or dataset. The majority of existing approaches focus on anomaly or fault detection in a specific class of images or environments, while general-purpose visual anomaly detection algorithms are more scarce in the literature. In this paper, we propose a comprehensive deep learning framework for detecting anomalies and changes in a priori unknown environments after a reference dataset is gathered, and without need for retraining the model. We use the SuperPoint and SuperGlue feature extraction and matching methods to detect anomalies based on reference images taken from a similar location and with partial overlapping of the field of view. We also introduce a self-calibrating method for the proposed model in order to address the problem of sensitivity to feature matching thresholds and environmental conditions. To evaluate the proposed framework, we have used a ground robot system for the purpose of reference and query data collection. We show that high accuracy can be obtained using the proposed method. We also show that the calibration process enhances changes and foreign object detection performance.","PeriodicalId":282759,"journal":{"name":"2022 Sixth IEEE International Conference on Robotic Computing (IRC)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125676379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-09DOI: 10.1109/IRC55401.2022.00047
Joshua Springer, M. Kyas
Precision landing is a remaining challenge in autonomous drone flight. Fiducial markers provide a computationally cheap way for a drone to locate a landing pad and autonomously execute precision landings. However, most work in this field depends on either rigidly-mounted or downward-facing cameras which restrict the drone’s ability to detect the marker. We present a method of autonomous landing that uses a gimbal-mounted camera to quickly search for the landing pad by simply spinning in place while tilting the camera up and down, and to continually aim the camera at the landing pad during approach and landing. This method demonstrates successful search, tracking, and landing with 4 of 5 tested fiducial systems on a physical drone with no human intervention. Per fiducial system, we present the distributions of the distances from the drone to the center of the landing pad after each successful landing. We also show representative examples of flight trajectories, marker tracking performance, and control outputs for each channel during the landing. Finally, we discuss qualitative strengths and weaknesses underlying each system.
{"title":"Autonomous Drone Landing with Fiducial Markers and a Gimbal-Mounted Camera for Active Tracking","authors":"Joshua Springer, M. Kyas","doi":"10.1109/IRC55401.2022.00047","DOIUrl":"https://doi.org/10.1109/IRC55401.2022.00047","url":null,"abstract":"Precision landing is a remaining challenge in autonomous drone flight. Fiducial markers provide a computationally cheap way for a drone to locate a landing pad and autonomously execute precision landings. However, most work in this field depends on either rigidly-mounted or downward-facing cameras which restrict the drone’s ability to detect the marker. We present a method of autonomous landing that uses a gimbal-mounted camera to quickly search for the landing pad by simply spinning in place while tilting the camera up and down, and to continually aim the camera at the landing pad during approach and landing. This method demonstrates successful search, tracking, and landing with 4 of 5 tested fiducial systems on a physical drone with no human intervention. Per fiducial system, we present the distributions of the distances from the drone to the center of the landing pad after each successful landing. We also show representative examples of flight trajectories, marker tracking performance, and control outputs for each channel during the landing. Finally, we discuss qualitative strengths and weaknesses underlying each system.","PeriodicalId":282759,"journal":{"name":"2022 Sixth IEEE International Conference on Robotic Computing (IRC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126690945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-29DOI: 10.1109/IRC55401.2022.00017
Daniel Weber, Wolfgang Fuhl, A. Zell, Enkelejda Kasneci
I human-robot collaboration, one challenging task is to teach a robot new yet unknown objects enabling it to interact with them. Thereby, gaze can contain valuable information. We investigate if it is possible to detect objects (object or no object) merely from gaze data and determine their bounding box parameters. For this purpose, we explore different sizes of temporal windows, which serve as a basis for the computation of heatmaps, i.e., the spatial distribution of the gaze data. Additionally, we analyze different grid sizes of these heatmaps, and demonstrate the functionality in a proof of concept using different machine learning techniques. Our method is characterized by its speed and resource efficiency compared to conventional object detectors. In order to generate the required data, we conducted a study with five subjects who could move freely and thus, turn towards arbitrary objects. This way, we chose a scenario for our data collection that is as realistic as possible. Since the subjects move while facing objects, the heatmaps also contain gaze data trajectories, complicating the detection and parameter regression. We make our data set publicly available to the research community for download.
{"title":"Gaze-based Object Detection in the Wild","authors":"Daniel Weber, Wolfgang Fuhl, A. Zell, Enkelejda Kasneci","doi":"10.1109/IRC55401.2022.00017","DOIUrl":"https://doi.org/10.1109/IRC55401.2022.00017","url":null,"abstract":"I human-robot collaboration, one challenging task is to teach a robot new yet unknown objects enabling it to interact with them. Thereby, gaze can contain valuable information. We investigate if it is possible to detect objects (object or no object) merely from gaze data and determine their bounding box parameters. For this purpose, we explore different sizes of temporal windows, which serve as a basis for the computation of heatmaps, i.e., the spatial distribution of the gaze data. Additionally, we analyze different grid sizes of these heatmaps, and demonstrate the functionality in a proof of concept using different machine learning techniques. Our method is characterized by its speed and resource efficiency compared to conventional object detectors. In order to generate the required data, we conducted a study with five subjects who could move freely and thus, turn towards arbitrary objects. This way, we chose a scenario for our data collection that is as realistic as possible. Since the subjects move while facing objects, the heatmaps also contain gaze data trajectories, complicating the detection and parameter regression. We make our data set publicly available to the research community for download.","PeriodicalId":282759,"journal":{"name":"2022 Sixth IEEE International Conference on Robotic Computing (IRC)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128001186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-18DOI: 10.1109/IRC55401.2022.00054
Joshua Springer, M. Kyas
Fiducial systems provide a computationally cheap way for mobile robots to estimate the pose of objects, or their own pose, using just a monocular camera. However, the orientation component of the pose of fiducial markers is unreliable, which can have destructive effects in autonomous drone landing on landing pads marked with fiducial markers. This paper evaluates the April Tag and WhyCode fiducial systems in terms of orientation ambiguity and detection rate on embedded hardware. We test 2 April Tag variants – 1 default and 1 custom – and 3 Whycode variants – 1 default and 2 custom. We determine that they are suitable for autonomous drone landing applications in terms of detection rate, but may generate erroneous control signals as a result of orientation ambiguity in the pose estimates.
{"title":"Evaluation of Orientation Ambiguity and Detection Rate in April Tag and WhyCode","authors":"Joshua Springer, M. Kyas","doi":"10.1109/IRC55401.2022.00054","DOIUrl":"https://doi.org/10.1109/IRC55401.2022.00054","url":null,"abstract":"Fiducial systems provide a computationally cheap way for mobile robots to estimate the pose of objects, or their own pose, using just a monocular camera. However, the orientation component of the pose of fiducial markers is unreliable, which can have destructive effects in autonomous drone landing on landing pads marked with fiducial markers. This paper evaluates the April Tag and WhyCode fiducial systems in terms of orientation ambiguity and detection rate on embedded hardware. We test 2 April Tag variants – 1 default and 1 custom – and 3 Whycode variants – 1 default and 2 custom. We determine that they are suitable for autonomous drone landing applications in terms of detection rate, but may generate erroneous control signals as a result of orientation ambiguity in the pose estimates.","PeriodicalId":282759,"journal":{"name":"2022 Sixth IEEE International Conference on Robotic Computing (IRC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125234512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-28DOI: 10.1109/IRC55401.2022.00022
Adarsh Sehgal, Nicholas Ward, Hung M. La, C. Papachristos, S. Louis
Agents can base decisions made using reinforcement learning (RL) on a reward function. The selection of values for the learning algorithm parameters can, nevertheless, have a substantial impact on the overall learning process. In order to discover values for the learning parameters that are close to optimal, we extended our previously proposed genetic algorithm-based Deep Deterministic Policy Gradient and Hindsight Experience Replay approach (referred to as GA+DDPG+HER) in this study. On the robotic manipulation tasks of FetchReach, FetchSlide, FetchPush, FetchPick&Place, and DoorOpening, we applied the GA+DDPG+HER methodology. Our technique GA+DDPG+HER was also used in the AuboReach environment with a few adjustments. Our experimental analysis demonstrates that our method produces performance that is noticeably better and occurs faster than the original algorithm. We also offer proof that GA+DDPG+HER beat the current approaches. The final results support our assertion and offer sufficient proof that automating the parameter tuning procedure is crucial and does cut down learning time by as much as 57%.
{"title":"GA+DDPG+HER: Genetic Algorithm-Based Function Optimizer in Deep Reinforcement Learning for Robotic Manipulation Tasks","authors":"Adarsh Sehgal, Nicholas Ward, Hung M. La, C. Papachristos, S. Louis","doi":"10.1109/IRC55401.2022.00022","DOIUrl":"https://doi.org/10.1109/IRC55401.2022.00022","url":null,"abstract":"Agents can base decisions made using reinforcement learning (RL) on a reward function. The selection of values for the learning algorithm parameters can, nevertheless, have a substantial impact on the overall learning process. In order to discover values for the learning parameters that are close to optimal, we extended our previously proposed genetic algorithm-based Deep Deterministic Policy Gradient and Hindsight Experience Replay approach (referred to as GA+DDPG+HER) in this study. On the robotic manipulation tasks of FetchReach, FetchSlide, FetchPush, FetchPick&Place, and DoorOpening, we applied the GA+DDPG+HER methodology. Our technique GA+DDPG+HER was also used in the AuboReach environment with a few adjustments. Our experimental analysis demonstrates that our method produces performance that is noticeably better and occurs faster than the original algorithm. We also offer proof that GA+DDPG+HER beat the current approaches. The final results support our assertion and offer sufficient proof that automating the parameter tuning procedure is crucial and does cut down learning time by as much as 57%.","PeriodicalId":282759,"journal":{"name":"2022 Sixth IEEE International Conference on Robotic Computing (IRC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115536785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-30DOI: 10.1109/IRC55401.2022.00067
André Rosa de Sousa Porfírio Correia, L. Alexandre
This paper presents a framework for learning visual representations from unlabeled video demonstrations captured from multiple viewpoints. We show that these representations are applicable for imitating robotic tasks. We use contrastive learning to enhance task-relevant information while suppressing irrelevant information in the feature embeddings. We validate the proposed method on the publicly available Multi-View Pouring and a custom Pick and Place data sets and compare it with the TCN and CMC baselines. We evaluate the learned representations using three metrics: viewpoint alignment, stage classification and reinforcement learning. In all cases, the results improve when compared to state-of-the-art approaches.
{"title":"Multi-View Contrastive Learning from Demonstrations","authors":"André Rosa de Sousa Porfírio Correia, L. Alexandre","doi":"10.1109/IRC55401.2022.00067","DOIUrl":"https://doi.org/10.1109/IRC55401.2022.00067","url":null,"abstract":"This paper presents a framework for learning visual representations from unlabeled video demonstrations captured from multiple viewpoints. We show that these representations are applicable for imitating robotic tasks. We use contrastive learning to enhance task-relevant information while suppressing irrelevant information in the feature embeddings. We validate the proposed method on the publicly available Multi-View Pouring and a custom Pick and Place data sets and compare it with the TCN and CMC baselines. We evaluate the learned representations using three metrics: viewpoint alignment, stage classification and reinforcement learning. In all cases, the results improve when compared to state-of-the-art approaches.","PeriodicalId":282759,"journal":{"name":"2022 Sixth IEEE International Conference on Robotic Computing (IRC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133285026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：