Pub Date : 2022-06-27DOI: 10.15607/rss.2022.xviii.067
Tara Boroushaki, L. Dodds, Nazish Naeem, Fadel M. Adib
—Mechanical search is a robotic problem where a robot needs to retrieve a target item that is partially or fully-occluded from its camera. State-of-the-art approaches for me- chanical search either require an expensive search process to find the target item, or they require the item to be tagged with a radio frequency identification tag (e.g., RFID), making their approach beneficial only to tagged items in the environment. We present FuseBot, the first robotic system for RF-Visual mechanical search that enables efficient retrieval of both RF-tagged and untagged items in a pile. Rather than requiring all target items in a pile to be RF-tagged, FuseBot leverages the mere existence of an RF-tagged item in the pile to benefit both tagged and untagged items. Our design introduces two key innovations. The first is RF-Visual Mapping , a technique that identifies and locates RF-tagged items in a pile and uses this information to construct an RF-Visual occupancy distribution map. The second is RF-Visual Extraction , a policy formulated as an optimization problem that minimizes the number of actions required to extract the target object by accounting for the probabilistic occupancy distribution, the expected grasp quality, and the expected information gain from future actions. We built a real-time end-to-end prototype of our system on a UR5e robotic arm with in-hand vision and RF perception modules. We conducted over 180 real-world experimental trials to evaluate FuseBot and compare its performance to a state-of-the-art vision-based system named X-Ray [10]. Our experimental results demonstrate that FuseBot outperforms X-Ray’s efficiency by more than 40% in terms of the number of actions required for successful mechanical search. Furthermore, in comparison to X-Ray’s success rate of 84%, FuseBot achieves a success rate of 95% in retrieving untagged items, demonstrating for the first time that the benefits of RF perception extend beyond tagged objects in the mechanical search problem.
{"title":"FuseBot: RF-Visual Mechanical Search","authors":"Tara Boroushaki, L. Dodds, Nazish Naeem, Fadel M. Adib","doi":"10.15607/rss.2022.xviii.067","DOIUrl":"https://doi.org/10.15607/rss.2022.xviii.067","url":null,"abstract":"—Mechanical search is a robotic problem where a robot needs to retrieve a target item that is partially or fully-occluded from its camera. State-of-the-art approaches for me- chanical search either require an expensive search process to find the target item, or they require the item to be tagged with a radio frequency identification tag (e.g., RFID), making their approach beneficial only to tagged items in the environment. We present FuseBot, the first robotic system for RF-Visual mechanical search that enables efficient retrieval of both RF-tagged and untagged items in a pile. Rather than requiring all target items in a pile to be RF-tagged, FuseBot leverages the mere existence of an RF-tagged item in the pile to benefit both tagged and untagged items. Our design introduces two key innovations. The first is RF-Visual Mapping , a technique that identifies and locates RF-tagged items in a pile and uses this information to construct an RF-Visual occupancy distribution map. The second is RF-Visual Extraction , a policy formulated as an optimization problem that minimizes the number of actions required to extract the target object by accounting for the probabilistic occupancy distribution, the expected grasp quality, and the expected information gain from future actions. We built a real-time end-to-end prototype of our system on a UR5e robotic arm with in-hand vision and RF perception modules. We conducted over 180 real-world experimental trials to evaluate FuseBot and compare its performance to a state-of-the-art vision-based system named X-Ray [10]. Our experimental results demonstrate that FuseBot outperforms X-Ray’s efficiency by more than 40% in terms of the number of actions required for successful mechanical search. Furthermore, in comparison to X-Ray’s success rate of 84%, FuseBot achieves a success rate of 95% in retrieving untagged items, demonstrating for the first time that the benefits of RF perception extend beyond tagged objects in the mechanical search problem.","PeriodicalId":340265,"journal":{"name":"Robotics: Science and Systems XVIII","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130676933","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 : 2022-06-27DOI: 10.15607/rss.2022.xviii.043
D. Rakita, Bilge Mutlu, Michael Gleicher
—Many applications in robotics require computing a robot manipulator’s “proximity” to a collision state in a given configuration. This collision proximity is commonly framed as a summation over closest Euclidean distances between many pairs of rigid shapes in a scene. Computing many such pairwise distances is inefficient, while more efficient approximations of this procedure, such as through supervised learning, lack accuracy and robustness. In this work, we present an approach for computing a collision proximity function for robot manipulators that formalizes the trade-off between efficiency and accuracy and provides an algorithm that gives control over it. Our algorithm, called P ROXIMA , works in one of two ways: (1) given a time budget as input, the algorithm returns an as-accurate-as-possible proximity approximation value in this time; or (2) given an accuracy budget , the algorithm returns an as-fast-as-possible proximity approximation value that is within the given accuracy bounds. We show the robustness of our approach through analytical investigation and simulation experiments on a wide set of robot models ranging from 6 to 132 degrees of freedom. We demonstrate that controlling the trade-off between efficiency and accuracy in proximity computations via our approach can enable safe and accurate real-time robot motion-optimization even on high-dimensional robot models. a self-collision; end-effector translation error (summed in the case of robots with multiple end-effectors); end-effector rotation error in radians (summed in the case of robots with multiple end-effectors); and the average joint velocity.
{"title":"Proxima: An Approach for Time or Accuracy Budgeted Collision Proximity Queries","authors":"D. Rakita, Bilge Mutlu, Michael Gleicher","doi":"10.15607/rss.2022.xviii.043","DOIUrl":"https://doi.org/10.15607/rss.2022.xviii.043","url":null,"abstract":"—Many applications in robotics require computing a robot manipulator’s “proximity” to a collision state in a given configuration. This collision proximity is commonly framed as a summation over closest Euclidean distances between many pairs of rigid shapes in a scene. Computing many such pairwise distances is inefficient, while more efficient approximations of this procedure, such as through supervised learning, lack accuracy and robustness. In this work, we present an approach for computing a collision proximity function for robot manipulators that formalizes the trade-off between efficiency and accuracy and provides an algorithm that gives control over it. Our algorithm, called P ROXIMA , works in one of two ways: (1) given a time budget as input, the algorithm returns an as-accurate-as-possible proximity approximation value in this time; or (2) given an accuracy budget , the algorithm returns an as-fast-as-possible proximity approximation value that is within the given accuracy bounds. We show the robustness of our approach through analytical investigation and simulation experiments on a wide set of robot models ranging from 6 to 132 degrees of freedom. We demonstrate that controlling the trade-off between efficiency and accuracy in proximity computations via our approach can enable safe and accurate real-time robot motion-optimization even on high-dimensional robot models. a self-collision; end-effector translation error (summed in the case of robots with multiple end-effectors); end-effector rotation error in radians (summed in the case of robots with multiple end-effectors); and the average joint velocity.","PeriodicalId":340265,"journal":{"name":"Robotics: Science and Systems XVIII","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134150823","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 : 2022-06-27DOI: 10.15607/rss.2022.xviii.002
Fang Bai, A. Bartoli
—Simultaneous localization and mapping (SLAM) in the deformable environment has encountered several barricades. One of them is the lack of a global registration technique. Thus current SLAM systems heavily rely on template based methods. We propose KernelGPA, a novel global registration technique to bridge the gap. We define nonrigid transformations using a kernel method, and show that the principal axes of the map can be solved globally in closed-form, up to a global scale ambiguity along each axis. We propose to solve both the global scale ambiguity and rigid poses in a unified optimization framework, yielding a cost that can be readily incorporated in sensor fusion frameworks. We demonstrate the registration performance of KernelGPA using various datasets, with a special focus on computerized tomography (CT) registration. We release our code 1 and data to foster future research in this direction. in all cases, and the CVE-Gfold for most of cases. This clearly shows that
{"title":"KernelGPA: A Deformable SLAM Back-end","authors":"Fang Bai, A. Bartoli","doi":"10.15607/rss.2022.xviii.002","DOIUrl":"https://doi.org/10.15607/rss.2022.xviii.002","url":null,"abstract":"—Simultaneous localization and mapping (SLAM) in the deformable environment has encountered several barricades. One of them is the lack of a global registration technique. Thus current SLAM systems heavily rely on template based methods. We propose KernelGPA, a novel global registration technique to bridge the gap. We define nonrigid transformations using a kernel method, and show that the principal axes of the map can be solved globally in closed-form, up to a global scale ambiguity along each axis. We propose to solve both the global scale ambiguity and rigid poses in a unified optimization framework, yielding a cost that can be readily incorporated in sensor fusion frameworks. We demonstrate the registration performance of KernelGPA using various datasets, with a special focus on computerized tomography (CT) registration. We release our code 1 and data to foster future research in this direction. in all cases, and the CVE-Gfold for most of cases. This clearly shows that","PeriodicalId":340265,"journal":{"name":"Robotics: Science and Systems XVIII","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121982078","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 : 2022-06-27DOI: 10.15607/rss.2022.xviii.074
G. Tabor, Lan N. Pham, J. Abbott, Tucker Hermans
—This paper extends recent work in demonstrating magnetic manipulation of conductive, nonmagnetic objects using rotating magnetic dipole fields. The current state of the art demonstrates dexterous manipulation of solid copper spheres with all object parameters known a priori . Our approach expands the previous model that contained three discrete modes to a single, continuous model that covers all possible relative positions of the manipulated object relative to the magnetic field source. We further leverage this new model to examine manipulation of spherical objects with unknown physical parameters, by applying techniques from the online-optimization and adaptive-control literature. Our experimental results validate our new dynamics model, showing that we get comparable or improved performance to the previously proposed model, while solving a simpler optimization problem for control. We further demonstrate the first physical magnetic control of aluminum spheres, as previous controllers were only physically validated on copper spheres. We show that our adaptive control framework can quickly acquire accurate estimates of the true spherical radius when weakly initialized, enabling control of spheres with unknown physical properties. Finally, we demonstrate that the spherical- object model can be used as an approximate model for adaptive control of nonspherical objects by performing the first magnetic manipulation of nonspherical, nonmagnetic objects.
{"title":"Adaptive Manipulation of Conductive, Nonmagnetic Objects via a Continuous Model of Magnetically Induced Force and Torque","authors":"G. Tabor, Lan N. Pham, J. Abbott, Tucker Hermans","doi":"10.15607/rss.2022.xviii.074","DOIUrl":"https://doi.org/10.15607/rss.2022.xviii.074","url":null,"abstract":"—This paper extends recent work in demonstrating magnetic manipulation of conductive, nonmagnetic objects using rotating magnetic dipole fields. The current state of the art demonstrates dexterous manipulation of solid copper spheres with all object parameters known a priori . Our approach expands the previous model that contained three discrete modes to a single, continuous model that covers all possible relative positions of the manipulated object relative to the magnetic field source. We further leverage this new model to examine manipulation of spherical objects with unknown physical parameters, by applying techniques from the online-optimization and adaptive-control literature. Our experimental results validate our new dynamics model, showing that we get comparable or improved performance to the previously proposed model, while solving a simpler optimization problem for control. We further demonstrate the first physical magnetic control of aluminum spheres, as previous controllers were only physically validated on copper spheres. We show that our adaptive control framework can quickly acquire accurate estimates of the true spherical radius when weakly initialized, enabling control of spheres with unknown physical properties. Finally, we demonstrate that the spherical- object model can be used as an approximate model for adaptive control of nonspherical objects by performing the first magnetic manipulation of nonspherical, nonmagnetic objects.","PeriodicalId":340265,"journal":{"name":"Robotics: Science and Systems XVIII","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125938818","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 : 2022-06-27DOI: 10.15607/rss.2022.xviii.006
Peer Neubert, Stefan Schubert
—Image descriptor based place recognition is an im- portant means for loop-closure detection in SLAM. The currently best performing image descriptors for this task are trained on large training datasets with the goal to be applicable in many different environments. In particular, they are not optimized for a specific environment, e.g. the city of Oxford. However, we argue that for place recognition, there is always a specific environment – not necessarily geographically defined, but specified by the particular set of descriptors in the database. In this paper, we propose SEER, a simple and efficient algorithm that can learn to create better descriptors for a specific environment from such a potentially very small set of database descriptors. The new descriptors are better in the sense that they will be more suited for image retrieval on these database descriptors. SEER stands for Sparse Exemplar Ensemble Representations. Both sparsity and ensemble representations are necessary components of the proposed approach. This is evaluated on a large variety of standard place recognition datasets where SEER considerably outperforms existing methods. It does not require any label information and is applicable in online place recognition scenarios. Open source code is available. 1
{"title":"SEER: Unsupervised and sample-efficient environment specialization of image descriptors","authors":"Peer Neubert, Stefan Schubert","doi":"10.15607/rss.2022.xviii.006","DOIUrl":"https://doi.org/10.15607/rss.2022.xviii.006","url":null,"abstract":"—Image descriptor based place recognition is an im- portant means for loop-closure detection in SLAM. The currently best performing image descriptors for this task are trained on large training datasets with the goal to be applicable in many different environments. In particular, they are not optimized for a specific environment, e.g. the city of Oxford. However, we argue that for place recognition, there is always a specific environment – not necessarily geographically defined, but specified by the particular set of descriptors in the database. In this paper, we propose SEER, a simple and efficient algorithm that can learn to create better descriptors for a specific environment from such a potentially very small set of database descriptors. The new descriptors are better in the sense that they will be more suited for image retrieval on these database descriptors. SEER stands for Sparse Exemplar Ensemble Representations. Both sparsity and ensemble representations are necessary components of the proposed approach. This is evaluated on a large variety of standard place recognition datasets where SEER considerably outperforms existing methods. It does not require any label information and is applicable in online place recognition scenarios. Open source code is available. 1","PeriodicalId":340265,"journal":{"name":"Robotics: Science and Systems XVIII","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134335718","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 : 2022-06-27DOI: 10.15607/rss.2022.xviii.024
Michael Fulton, Muntaqim Mehtaz, Junaed Sattar, Owen Queeglay
—Autonomous underwater vehicles (AUVs) have long lagged behind other types of robots in supporting natural communication modes for human-robot interaction. Due to the limitations of the environment, most AUVs use digital displays or topside human-in-the-loop communications as their primary or only communication vectors. Natural methods for robot-to-human communication such as robot “gestures” have been proposed, but never evaluated on non-simulated AUVs. In this paper, we enhance, implement and evaluate a robot-to-human communication system for AUVs called Robot Communication Via Motion (RCVM), which utilizes explicit motion phrases (kinemes) to communicate with a dive partner. We present a small pilot study that shows our implementation to be reasonably effec- tive in person followed by a large-population study, comparing the communication effectiveness of our RCVM implementation to three baseline systems. Our results establish RCVM as an effective method of robot-to-human communication underwater and reveal the differences with more traditional communication vectors in how accurately communication is achieved at different viewpoints and types of information payloads.
{"title":"Underwater Robot-To-Human Communication Via Motion: Implementation and Full-Loop Human Interface Evaluation","authors":"Michael Fulton, Muntaqim Mehtaz, Junaed Sattar, Owen Queeglay","doi":"10.15607/rss.2022.xviii.024","DOIUrl":"https://doi.org/10.15607/rss.2022.xviii.024","url":null,"abstract":"—Autonomous underwater vehicles (AUVs) have long lagged behind other types of robots in supporting natural communication modes for human-robot interaction. Due to the limitations of the environment, most AUVs use digital displays or topside human-in-the-loop communications as their primary or only communication vectors. Natural methods for robot-to-human communication such as robot “gestures” have been proposed, but never evaluated on non-simulated AUVs. In this paper, we enhance, implement and evaluate a robot-to-human communication system for AUVs called Robot Communication Via Motion (RCVM), which utilizes explicit motion phrases (kinemes) to communicate with a dive partner. We present a small pilot study that shows our implementation to be reasonably effec- tive in person followed by a large-population study, comparing the communication effectiveness of our RCVM implementation to three baseline systems. Our results establish RCVM as an effective method of robot-to-human communication underwater and reveal the differences with more traditional communication vectors in how accurately communication is achieved at different viewpoints and types of information payloads.","PeriodicalId":340265,"journal":{"name":"Robotics: Science and Systems XVIII","volume":"50 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113993242","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 : 2022-06-27DOI: 10.15607/rss.2022.xviii.061
Siyuan Xu, Minghui Zhu
—This paper considers policy-centric optimal motion planning with limited reaction time. The motion planning queries are determined by their goal regions and cost functionals, and are generated over time from a distribution. Once a new query is requested, the robot needs to quickly generate a motion planner which can steer the robot to the goal region while minimizing a cost functional. We develop a meta-learning-based algorithm to compute a meta value function, which can be fast adapted using a small number of samples of a new query. Simulations on a unicycle are conducted to evaluate the developed algorithm and show the anytime property of the proposed algorithm.
{"title":"Meta Value Learning for Fast Policy-Centric Optimal Motion Planning","authors":"Siyuan Xu, Minghui Zhu","doi":"10.15607/rss.2022.xviii.061","DOIUrl":"https://doi.org/10.15607/rss.2022.xviii.061","url":null,"abstract":"—This paper considers policy-centric optimal motion planning with limited reaction time. The motion planning queries are determined by their goal regions and cost functionals, and are generated over time from a distribution. Once a new query is requested, the robot needs to quickly generate a motion planner which can steer the robot to the goal region while minimizing a cost functional. We develop a meta-learning-based algorithm to compute a meta value function, which can be fast adapted using a small number of samples of a new query. Simulations on a unicycle are conducted to evaluate the developed algorithm and show the anytime property of the proposed algorithm.","PeriodicalId":340265,"journal":{"name":"Robotics: Science and Systems XVIII","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114231612","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 : 2022-06-27DOI: 10.15607/rss.2022.xviii.029
Hao Ma, Dieter Büchler, B. Scholkopf, Michael Muehlebach
—In this work, we propose a new learning-based iterative control (IC) framework that enables a complex soft-robotic arm to track trajectories accurately. Compared to tra- ditional iterative learning control (ILC), which operates on a single fixed reference trajectory, we use a deep learning approach to generalize across various reference trajectories. The resulting nonlinear mapping computes feedforward actions and is used in a two degrees of freedom control design. Our method incorporates prior knowledge about the system dynamics and by learning only feedforward actions, it mitigates the risk of instability. We demonstrate a low sample complexity and an excellent tracking performance in real-world experiments. The experiments are carried out on a custom-made robot arm with four degrees of freedom that is actuated with pneumatic artificial muscles. The experiments include high acceleration and high velocity motion.
{"title":"A Learning-based Iterative Control Framework for Controlling a Robot Arm with Pneumatic Artificial Muscles","authors":"Hao Ma, Dieter Büchler, B. Scholkopf, Michael Muehlebach","doi":"10.15607/rss.2022.xviii.029","DOIUrl":"https://doi.org/10.15607/rss.2022.xviii.029","url":null,"abstract":"—In this work, we propose a new learning-based iterative control (IC) framework that enables a complex soft-robotic arm to track trajectories accurately. Compared to tra- ditional iterative learning control (ILC), which operates on a single fixed reference trajectory, we use a deep learning approach to generalize across various reference trajectories. The resulting nonlinear mapping computes feedforward actions and is used in a two degrees of freedom control design. Our method incorporates prior knowledge about the system dynamics and by learning only feedforward actions, it mitigates the risk of instability. We demonstrate a low sample complexity and an excellent tracking performance in real-world experiments. The experiments are carried out on a custom-made robot arm with four degrees of freedom that is actuated with pneumatic artificial muscles. The experiments include high acceleration and high velocity motion.","PeriodicalId":340265,"journal":{"name":"Robotics: Science and Systems XVIII","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114232619","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 : 2022-06-27DOI: 10.15607/rss.2022.xviii.028
N. Gopalan, Nina Moorman, Manisha Natarajan, M. Gombolay
—Learning from demonstration (LfD) seeks to democ- ratize robotics by enabling non-experts to intuitively program robots to perform novel skills through human task demonstration. Yet, LfD is challenging under a task and motion planning setting which requires hierarchical abstractions. Prior work has studied mechanisms for eliciting demonstrations that include hierarchical specifications of task and motion, via keyframes [1] or hierarchical task network specifications [2]. However, such prior works have not examined whether non-roboticist end- users are capable of providing such hierarchical demonstrations without explicit training from a roboticist showing how to teach each task [3]. To address the limitations and assumptions of prior work, we conduct two novel human-subjects experiments to answer (1) what are the necessary conditions to teach users through hierarchy and task abstractions and (2) what instruc- tional information or feedback is required to support users to learn to program robots effectively to solve novel tasks. Our first experiment shows that fewer than half ( 35 . 71% ) of our subjects provide demonstrations with sub-task abstractions when not primed. Our second experiment demonstrates that users fail to teach the robot correctly when not shown a video demonstration of an expert’s teaching strategy for the exact task that the subject is training. Not even showing the video of an analogue task was sufficient. These experiments reveal the need for fundamentally different approaches in LfD which can allow end-users to teach generalizable long-horizon tasks to robots without the need to be coached by experts at every step.
{"title":"Negative Result for Learning from Demonstration: Challenges for End-Users Teaching Robots with Task And Motion Planning Abstractions","authors":"N. Gopalan, Nina Moorman, Manisha Natarajan, M. Gombolay","doi":"10.15607/rss.2022.xviii.028","DOIUrl":"https://doi.org/10.15607/rss.2022.xviii.028","url":null,"abstract":"—Learning from demonstration (LfD) seeks to democ- ratize robotics by enabling non-experts to intuitively program robots to perform novel skills through human task demonstration. Yet, LfD is challenging under a task and motion planning setting which requires hierarchical abstractions. Prior work has studied mechanisms for eliciting demonstrations that include hierarchical specifications of task and motion, via keyframes [1] or hierarchical task network specifications [2]. However, such prior works have not examined whether non-roboticist end- users are capable of providing such hierarchical demonstrations without explicit training from a roboticist showing how to teach each task [3]. To address the limitations and assumptions of prior work, we conduct two novel human-subjects experiments to answer (1) what are the necessary conditions to teach users through hierarchy and task abstractions and (2) what instruc- tional information or feedback is required to support users to learn to program robots effectively to solve novel tasks. Our first experiment shows that fewer than half ( 35 . 71% ) of our subjects provide demonstrations with sub-task abstractions when not primed. Our second experiment demonstrates that users fail to teach the robot correctly when not shown a video demonstration of an expert’s teaching strategy for the exact task that the subject is training. Not even showing the video of an analogue task was sufficient. These experiments reveal the need for fundamentally different approaches in LfD which can allow end-users to teach generalizable long-horizon tasks to robots without the need to be coached by experts at every step.","PeriodicalId":340265,"journal":{"name":"Robotics: Science and Systems XVIII","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122566452","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 : 2022-06-27DOI: 10.15607/rss.2022.xviii.073
Christian Lanegger, Marco Ruggia, M. Tognon, Lionel Ott, R. Siegwart
—Aerial robots have demonstrated impressive feats of precise control, such as dynamic flight through openings or highly complex choreographies. Despite the accuracy needed for these tasks, there are problems that require levels of precision that are challenging to achieve today. One such problem is aerial interaction. Advances in aerial robot design and control have made such contact-based tasks possible and opened up research into challenging real-world tasks, including contact-based inspection. However, while centimetre accuracy is sufficient and achievable for inspection tasks, the positioning accuracy needed for other problems, such as layouting on construction sites or general push-and-slide tasks, is millimetres. To achieve such a high precision, we propose a new aerial system composed of an aerial vehicle equipped with a novel “smart” end-effector leveraging a stability-optimized Gough-Stewart mechanism. We present its design process and features incorporating the princi-ples of compliance, multiple contact points, actuation, and self- containment. In experiments, we verify that the design choices made for our novel end-effector are necessary to obtain the desired positioning precision. Furthermore, we demonstrate that we can reliably mark lines on ceilings with millimetre accuracy without the need for precise modeling or sophisticated control of the aerial robot.
{"title":"Aerial Layouting: Design and Control of a Compliant and Actuated End-Effector for Precise In-flight Marking on Ceilings","authors":"Christian Lanegger, Marco Ruggia, M. Tognon, Lionel Ott, R. Siegwart","doi":"10.15607/rss.2022.xviii.073","DOIUrl":"https://doi.org/10.15607/rss.2022.xviii.073","url":null,"abstract":"—Aerial robots have demonstrated impressive feats of precise control, such as dynamic flight through openings or highly complex choreographies. Despite the accuracy needed for these tasks, there are problems that require levels of precision that are challenging to achieve today. One such problem is aerial interaction. Advances in aerial robot design and control have made such contact-based tasks possible and opened up research into challenging real-world tasks, including contact-based inspection. However, while centimetre accuracy is sufficient and achievable for inspection tasks, the positioning accuracy needed for other problems, such as layouting on construction sites or general push-and-slide tasks, is millimetres. To achieve such a high precision, we propose a new aerial system composed of an aerial vehicle equipped with a novel “smart” end-effector leveraging a stability-optimized Gough-Stewart mechanism. We present its design process and features incorporating the princi-ples of compliance, multiple contact points, actuation, and self- containment. In experiments, we verify that the design choices made for our novel end-effector are necessary to obtain the desired positioning precision. Furthermore, we demonstrate that we can reliably mark lines on ceilings with millimetre accuracy without the need for precise modeling or sophisticated control of the aerial robot.","PeriodicalId":340265,"journal":{"name":"Robotics: Science and Systems XVIII","volume":"609 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116451568","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：