Pub Date : 2023-02-02DOI: 10.1177/02783649231154674
Sihui Li, Neil T. Dantam
We present a learning-based approach to prove infeasibility of kinematic motion planning problems. Sampling-based motion planners are effective in high-dimensional spaces but are only probabilistically complete. Consequently, these planners cannot provide a definite answer if no plan exists, which is important for high-level scenarios, such as task-motion planning. We apply data generated during multi-directional sampling-based planning (such as PRM) to a machine learning approach to construct an infeasibility proof. An infeasibility proof is a closed manifold in the obstacle region of the configuration space that separates the start and goal into disconnected components of the free configuration space. We train the manifold using common machine learning techniques and then triangulate the manifold into a polytope to prove containment in the obstacle region. Under assumptions about the hyper-parameters and robustness of configuration space optimization, the output is either an infeasibility proof or a motion plan in the limit. We demonstrate proof construction for up to 4-DOF configuration spaces. A large part of the algorithm is parallelizable, which offers potential to address higher dimensional configuration spaces.
{"title":"A sampling and learning framework to prove motion planning infeasibility","authors":"Sihui Li, Neil T. Dantam","doi":"10.1177/02783649231154674","DOIUrl":"https://doi.org/10.1177/02783649231154674","url":null,"abstract":"We present a learning-based approach to prove infeasibility of kinematic motion planning problems. Sampling-based motion planners are effective in high-dimensional spaces but are only probabilistically complete. Consequently, these planners cannot provide a definite answer if no plan exists, which is important for high-level scenarios, such as task-motion planning. We apply data generated during multi-directional sampling-based planning (such as PRM) to a machine learning approach to construct an infeasibility proof. An infeasibility proof is a closed manifold in the obstacle region of the configuration space that separates the start and goal into disconnected components of the free configuration space. We train the manifold using common machine learning techniques and then triangulate the manifold into a polytope to prove containment in the obstacle region. Under assumptions about the hyper-parameters and robustness of configuration space optimization, the output is either an infeasibility proof or a motion plan in the limit. We demonstrate proof construction for up to 4-DOF configuration spaces. A large part of the algorithm is parallelizable, which offers potential to address higher dimensional configuration spaces.","PeriodicalId":54942,"journal":{"name":"International Journal of Robotics Research","volume":null,"pages":null},"PeriodicalIF":9.2,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48377278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.1177/02783649231153958
Martin Gurtner, J. Zemánek, Z. Hurák
This paper proposes an algorithm for decomposing and possibly distributing an optimization problem that naturally emerges in distributed manipulation by shaping physical force fields through actuators distributed in space (arrays of actuators). One or several manipulated objects located in this field can “feel the force” and move simultaneously and independently. The control system has to produce commands for all actuators so that desired forces are developed at several prescribed places. This can be formulated as an optimization problem that has to be solved in every sampling period. Exploiting the structure of the optimization problem is crucial for platforms with many actuators and many manipulated objects, hence the goal of decomposing the huge optimization problem into several subproblems. Furthermore, if the platform is composed of interconnected actuator modules with computational capabilities, the decomposition can give guidance for the distribution of the computation to the modules. We propose an algorithm for decomposing/distributing the optimization problem using Alternating Direction Method of Multipliers (ADMM). The proposed algorithm is shown to converge to modest accuracy for various distributed platforms in a few iterations. We demonstrate our algorithm through numerical experiments corresponding to three physical experimental platforms for distributed manipulation using electric, magnetic, and pressure fields. Furthermore, we deploy and test it on real experimental platforms for distributed manipulation using an array of solenoids and ultrasonic transducers.
{"title":"Alternating direction method of multipliers-based distributed control for distributed manipulation by shaping physical force fields","authors":"Martin Gurtner, J. Zemánek, Z. Hurák","doi":"10.1177/02783649231153958","DOIUrl":"https://doi.org/10.1177/02783649231153958","url":null,"abstract":"This paper proposes an algorithm for decomposing and possibly distributing an optimization problem that naturally emerges in distributed manipulation by shaping physical force fields through actuators distributed in space (arrays of actuators). One or several manipulated objects located in this field can “feel the force” and move simultaneously and independently. The control system has to produce commands for all actuators so that desired forces are developed at several prescribed places. This can be formulated as an optimization problem that has to be solved in every sampling period. Exploiting the structure of the optimization problem is crucial for platforms with many actuators and many manipulated objects, hence the goal of decomposing the huge optimization problem into several subproblems. Furthermore, if the platform is composed of interconnected actuator modules with computational capabilities, the decomposition can give guidance for the distribution of the computation to the modules. We propose an algorithm for decomposing/distributing the optimization problem using Alternating Direction Method of Multipliers (ADMM). The proposed algorithm is shown to converge to modest accuracy for various distributed platforms in a few iterations. We demonstrate our algorithm through numerical experiments corresponding to three physical experimental platforms for distributed manipulation using electric, magnetic, and pressure fields. Furthermore, we deploy and test it on real experimental platforms for distributed manipulation using an array of solenoids and ultrasonic transducers.","PeriodicalId":54942,"journal":{"name":"International Journal of Robotics Research","volume":null,"pages":null},"PeriodicalIF":9.2,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43243936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-21DOI: 10.1177/02783649221128843
S. Lilge, T. Barfoot, J. Burgner-Kahrs
Continuum robots have the potential to enable new applications in medicine, inspection, and countless other areas due to their unique shape, compliance, and size. Excellent progress has been made in the mechanical design and dynamic modeling of continuum robots, to the point that there are some canonical designs, although new concepts continue to be explored. In this paper, we turn to the problem of state estimation for continuum robots that can been modeled with the common Cosserat rod model. Sensing for continuum robots might comprise external camera observations, embedded tracking coils, or strain gauges. We repurpose a Gaussian process (GP) regression approach to state estimation, initially developed for continuous-time trajectory estimation in SE(3). In our case, the continuous variable is not time but arclength and we show how to estimate the continuous shape (and strain) of the robot (along with associated uncertainties) given discrete, noisy measurements of both pose and strain along the length. We demonstrate our approach quantitatively through simulations as well as through experiments. Our evaluations show that accurate and continuous estimates of a continuum robot’s shape can be achieved, resulting in average end-effector errors between the estimated and ground truth shape as low as 3.5 mm and 0.016° in simulation or 3.3 mm and 0.035° for unloaded configurations and 6.2 mm and 0.041° for loaded ones during experiments, when using discrete pose measurements.
{"title":"Continuum robot state estimation using Gaussian process regression on S E ( 3 )","authors":"S. Lilge, T. Barfoot, J. Burgner-Kahrs","doi":"10.1177/02783649221128843","DOIUrl":"https://doi.org/10.1177/02783649221128843","url":null,"abstract":"Continuum robots have the potential to enable new applications in medicine, inspection, and countless other areas due to their unique shape, compliance, and size. Excellent progress has been made in the mechanical design and dynamic modeling of continuum robots, to the point that there are some canonical designs, although new concepts continue to be explored. In this paper, we turn to the problem of state estimation for continuum robots that can been modeled with the common Cosserat rod model. Sensing for continuum robots might comprise external camera observations, embedded tracking coils, or strain gauges. We repurpose a Gaussian process (GP) regression approach to state estimation, initially developed for continuous-time trajectory estimation in SE(3). In our case, the continuous variable is not time but arclength and we show how to estimate the continuous shape (and strain) of the robot (along with associated uncertainties) given discrete, noisy measurements of both pose and strain along the length. We demonstrate our approach quantitatively through simulations as well as through experiments. Our evaluations show that accurate and continuous estimates of a continuum robot’s shape can be achieved, resulting in average end-effector errors between the estimated and ground truth shape as low as 3.5 mm and 0.016° in simulation or 3.3 mm and 0.035° for unloaded configurations and 6.2 mm and 0.041° for loaded ones during experiments, when using discrete pose measurements.","PeriodicalId":54942,"journal":{"name":"International Journal of Robotics Research","volume":null,"pages":null},"PeriodicalIF":9.2,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49387090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-02DOI: 10.1177/02783649221120029
O. Khatib, Mikael Jorda, Jaeheung Park, L. Sentis, S. Chung
We present a comprehensive formulation to the problem of controlling a high-dimensional robotic system involving complex tasks subject to a variety of constraints, obstacles, balance, and contact challenges. Using intuitive and natural representations, the approach is initiated by establishing individual objectives for a task and its constraints. Simple independent controllers using artificial potential fields are then designed for each objective to reach goals while enforcing the constraints. Dynamically consistent projections in nullspaces associated with task and constraint representations are employed to deliver a coherent whole-body robot control. In multi-link multi-contact tasks, contact forces produce both resulting and internal forces. Internal forces play a critical role in robot balance and stability, achieved in this framework through modeling and controlling virtual linkages that explicitly describe the relationship between active/passive contact force, resultant force, controlled/uncontrolled internal force for multi-link multi-contact underactuated robots. Control of contacts with the environment involves material considerations such as friction and geometric constraints. Potential barriers direct the selection of contact forces ensuring stability and balance. This approach of dynamic projection and the Virtual Linkage Model addresses robot underactuation. In addition, the framework introduces a coordinate completion mechanism to establish a generalized coordinates representation of the task, removing redundancy and maintaining the full operational space dynamics description. This enables task-space dynamic control based on the relevant inertial properties. We present the experimental validation on a physical humanoid platform.
{"title":"Constraint-consistent task-oriented whole-body robot formulation: Task, posture, constraints, multiple contacts, and balance","authors":"O. Khatib, Mikael Jorda, Jaeheung Park, L. Sentis, S. Chung","doi":"10.1177/02783649221120029","DOIUrl":"https://doi.org/10.1177/02783649221120029","url":null,"abstract":"We present a comprehensive formulation to the problem of controlling a high-dimensional robotic system involving complex tasks subject to a variety of constraints, obstacles, balance, and contact challenges. Using intuitive and natural representations, the approach is initiated by establishing individual objectives for a task and its constraints. Simple independent controllers using artificial potential fields are then designed for each objective to reach goals while enforcing the constraints. Dynamically consistent projections in nullspaces associated with task and constraint representations are employed to deliver a coherent whole-body robot control. In multi-link multi-contact tasks, contact forces produce both resulting and internal forces. Internal forces play a critical role in robot balance and stability, achieved in this framework through modeling and controlling virtual linkages that explicitly describe the relationship between active/passive contact force, resultant force, controlled/uncontrolled internal force for multi-link multi-contact underactuated robots. Control of contacts with the environment involves material considerations such as friction and geometric constraints. Potential barriers direct the selection of contact forces ensuring stability and balance. This approach of dynamic projection and the Virtual Linkage Model addresses robot underactuation. In addition, the framework introduces a coordinate completion mechanism to establish a generalized coordinates representation of the task, removing redundancy and maintaining the full operational space dynamics description. This enables task-space dynamic control based on the relevant inertial properties. We present the experimental validation on a physical humanoid platform.","PeriodicalId":54942,"journal":{"name":"International Journal of Robotics Research","volume":null,"pages":null},"PeriodicalIF":9.2,"publicationDate":"2022-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42654951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-09DOI: 10.1177/02783649231153020
Shailesh Nirgudkar, M. Defilippo, Michael Sacarny, M. Benjamin, P. Robinette
Recent advances in deep learning technology have triggered radical progress in the autonomy of ground vehicles. Marine coastal Autonomous Surface Vehicles (ASVs) that are regularly used for surveillance, monitoring, and other routine tasks can benefit from this autonomy. Long haul deep sea transportation activities are additional opportunities. These two use cases present very different terrains—the first being coastal waters—with many obstacles, structures, and human presence while the latter is mostly devoid of such obstacles. Variations in environmental conditions are common to both terrains. Robust labeled datasets mapping such terrains are crucial in improving the situational awareness that can drive autonomy. However, there are only limited such maritime datasets available and these primarily consist of optical images. Although, long wave infrared (LWIR) is a strong complement to the optical spectrum that helps in extreme light conditions, a labeled public dataset with LWIR images does not currently exist. In this paper, we fill this gap by presenting a labeled dataset of over 2900 LWIR segmented images captured in coastal maritime environment over a period of 2 years. The images are labeled using instance segmentation and classified into seven categories—sky, water, obstacle, living obstacle, bridge, self, and background. We also evaluate this dataset across three deep learning architectures (UNet, PSPNet, DeepLabv3) and provide detailed analysis of its efficacy. While the dataset focuses on the coastal terrain, it can equally help deep sea use cases. Such terrain would have less traffic, and the classifier trained on cluttered environment would be able to handle sparse scenes effectively. We share this dataset with the research community with the hope that it spurs new scene understanding capabilities in the maritime environment.
{"title":"MassMIND: Massachusetts Maritime INfrared Dataset","authors":"Shailesh Nirgudkar, M. Defilippo, Michael Sacarny, M. Benjamin, P. Robinette","doi":"10.1177/02783649231153020","DOIUrl":"https://doi.org/10.1177/02783649231153020","url":null,"abstract":"Recent advances in deep learning technology have triggered radical progress in the autonomy of ground vehicles. Marine coastal Autonomous Surface Vehicles (ASVs) that are regularly used for surveillance, monitoring, and other routine tasks can benefit from this autonomy. Long haul deep sea transportation activities are additional opportunities. These two use cases present very different terrains—the first being coastal waters—with many obstacles, structures, and human presence while the latter is mostly devoid of such obstacles. Variations in environmental conditions are common to both terrains. Robust labeled datasets mapping such terrains are crucial in improving the situational awareness that can drive autonomy. However, there are only limited such maritime datasets available and these primarily consist of optical images. Although, long wave infrared (LWIR) is a strong complement to the optical spectrum that helps in extreme light conditions, a labeled public dataset with LWIR images does not currently exist. In this paper, we fill this gap by presenting a labeled dataset of over 2900 LWIR segmented images captured in coastal maritime environment over a period of 2 years. The images are labeled using instance segmentation and classified into seven categories—sky, water, obstacle, living obstacle, bridge, self, and background. We also evaluate this dataset across three deep learning architectures (UNet, PSPNet, DeepLabv3) and provide detailed analysis of its efficacy. While the dataset focuses on the coastal terrain, it can equally help deep sea use cases. Such terrain would have less traffic, and the classifier trained on cluttered environment would be able to handle sparse scenes effectively. We share this dataset with the research community with the hope that it spurs new scene understanding capabilities in the maritime environment.","PeriodicalId":54942,"journal":{"name":"International Journal of Robotics Research","volume":null,"pages":null},"PeriodicalIF":9.2,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41850155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-22DOI: 10.1177/02783649231168954
Vincent Wall, Gabriel Zöller, O. Brock
We propose a sensorization method for soft pneumatic actuators that uses an embedded microphone and speaker to measure different actuator properties. The physical state of the actuator determines the specific modulation of sound as it travels through the structure. Using simple machine learning, we create a computational sensor that infers the corresponding state from sound recordings. We demonstrate the acoustic sensor on a soft pneumatic continuum actuator and use it to measure contact locations, contact forces, object materials, actuator inflation, and actuator temperature. We show that the sensor is reliable (average classification rate for six contact locations of 93%), precise (mean spatial accuracy of 3.7 mm), and robust against common disturbances like background noise. Finally, we compare different sounds and learning methods and achieve best results with 20 ms of white noise and a support vector classifier as the sensor model.
{"title":"Passive and active acoustic sensing for soft pneumatic actuators","authors":"Vincent Wall, Gabriel Zöller, O. Brock","doi":"10.1177/02783649231168954","DOIUrl":"https://doi.org/10.1177/02783649231168954","url":null,"abstract":"We propose a sensorization method for soft pneumatic actuators that uses an embedded microphone and speaker to measure different actuator properties. The physical state of the actuator determines the specific modulation of sound as it travels through the structure. Using simple machine learning, we create a computational sensor that infers the corresponding state from sound recordings. We demonstrate the acoustic sensor on a soft pneumatic continuum actuator and use it to measure contact locations, contact forces, object materials, actuator inflation, and actuator temperature. We show that the sensor is reliable (average classification rate for six contact locations of 93%), precise (mean spatial accuracy of 3.7 mm), and robust against common disturbances like background noise. Finally, we compare different sounds and learning methods and achieve best results with 20 ms of white noise and a support vector classifier as the sensor model.","PeriodicalId":54942,"journal":{"name":"International Journal of Robotics Research","volume":null,"pages":null},"PeriodicalIF":9.2,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44060161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-18DOI: 10.1177/02783649221112446
Moju Zhao, K. Okada, M. Inaba
Various state-of-the-art works have achieved aerial manipulation and grasping by attaching additional manipulator to aerial robots. However, such a coupled platform has limitations with respect to the interaction force and mobility. In this paper, we present the successful implementation of aerial manipulation and grasping by a novel articulated aerial robot called DRAGON, in which a vectorable rotor unit is embedded in each link. The key to performing stable manipulation and grasping in the air is the usage of rotor vectoring apparatus having two degrees-of-freedom. First, a comprehensive flight control methodology for aerial transformation using the vectorable thrust force is developed with the consideration of the dynamics of vectoring actuators. This proposed control method can suppress the oscillation due to the dynamics of vectoring actuators and also allow the integration with external and internal wrenches for object manipulation and grasping. Second, an online thrust-level planning method for bimanual object grasping using the two ends of this articulated model is presented. The proposed grasping style is unique in that the vectorable thrust force is used as the internal wrench instead of the joint torque. Finally, we show the experimental results of evaluation on the proposed control and planning methods for object manipulation and grasping.
{"title":"Versatile articulated aerial robot DRAGON: Aerial manipulation and grasping by vectorable thrust control","authors":"Moju Zhao, K. Okada, M. Inaba","doi":"10.1177/02783649221112446","DOIUrl":"https://doi.org/10.1177/02783649221112446","url":null,"abstract":"Various state-of-the-art works have achieved aerial manipulation and grasping by attaching additional manipulator to aerial robots. However, such a coupled platform has limitations with respect to the interaction force and mobility. In this paper, we present the successful implementation of aerial manipulation and grasping by a novel articulated aerial robot called DRAGON, in which a vectorable rotor unit is embedded in each link. The key to performing stable manipulation and grasping in the air is the usage of rotor vectoring apparatus having two degrees-of-freedom. First, a comprehensive flight control methodology for aerial transformation using the vectorable thrust force is developed with the consideration of the dynamics of vectoring actuators. This proposed control method can suppress the oscillation due to the dynamics of vectoring actuators and also allow the integration with external and internal wrenches for object manipulation and grasping. Second, an online thrust-level planning method for bimanual object grasping using the two ends of this articulated model is presented. The proposed grasping style is unique in that the vectorable thrust force is used as the internal wrench instead of the joint torque. Finally, we show the experimental results of evaluation on the proposed control and planning methods for object manipulation and grasping.","PeriodicalId":54942,"journal":{"name":"International Journal of Robotics Research","volume":null,"pages":null},"PeriodicalIF":9.2,"publicationDate":"2022-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41363925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-01DOI: 10.1177/02783649221102980
Vitalii Pruks, J. Ryu
A virtual fixture (VF) is a constraint built into software that assists a human operator in moving a remote tool along a preferred path via an augmented guidance force to improve teleoperation performance. However, teleoperation generally applies to unknown or dynamic environments, which are challenging for VF use. Most researchers have assumed that VFs are pre-defined or generated automatically; however, these processes are complicated and unreliable in unknown environments where teleoperation is in high demand. Recently, a few researchers have addressed this issue by introducing a user-interactive method of generating VFs in unknown environments. However, these methods are limited to generating a single type of primitive for a single robot tool. Moreover, the accuracy of the VF generated by these methods depends on the accuracy of the human input. Thus, applications of these methods are limited. To overcome those limitations, this work introduces a novel interactive VF generation method that includes a new method of representing VFs as a composition of components. A feature-based user interface allows the human operator to intuitively specify the VF components. The new VF representation accommodates a variety of robot tools and actions. Using the feature-based interface, the process of VF generation is more intuitive and accurate. In this study, the proposed method is evaluated with human subjects in three teleoperation experiments: peg-in-hole, pipe-sawing, and pipe-welding. The experimental results show that the VFs generated by the proposed approach result in a higher manipulation quality while demonstrating the lowest total workload in all experiments. The peg-in-hole task teleoperation was the safest in terms of failure proportion and exerted force of the robot tool. In the pipe-sawing task, the positioning of the robot tool was the most accurate. In the pipe-welding task, the quality of weld was the best in terms of measured tool-trajectory smoothness and visual weld observation.
{"title":"Method for generating real-time interactive virtual fixture for shared teleoperation in unknown environments","authors":"Vitalii Pruks, J. Ryu","doi":"10.1177/02783649221102980","DOIUrl":"https://doi.org/10.1177/02783649221102980","url":null,"abstract":"A virtual fixture (VF) is a constraint built into software that assists a human operator in moving a remote tool along a preferred path via an augmented guidance force to improve teleoperation performance. However, teleoperation generally applies to unknown or dynamic environments, which are challenging for VF use. Most researchers have assumed that VFs are pre-defined or generated automatically; however, these processes are complicated and unreliable in unknown environments where teleoperation is in high demand. Recently, a few researchers have addressed this issue by introducing a user-interactive method of generating VFs in unknown environments. However, these methods are limited to generating a single type of primitive for a single robot tool. Moreover, the accuracy of the VF generated by these methods depends on the accuracy of the human input. Thus, applications of these methods are limited. To overcome those limitations, this work introduces a novel interactive VF generation method that includes a new method of representing VFs as a composition of components. A feature-based user interface allows the human operator to intuitively specify the VF components. The new VF representation accommodates a variety of robot tools and actions. Using the feature-based interface, the process of VF generation is more intuitive and accurate. In this study, the proposed method is evaluated with human subjects in three teleoperation experiments: peg-in-hole, pipe-sawing, and pipe-welding. The experimental results show that the VFs generated by the proposed approach result in a higher manipulation quality while demonstrating the lowest total workload in all experiments. The peg-in-hole task teleoperation was the safest in terms of failure proportion and exerted force of the robot tool. In the pipe-sawing task, the positioning of the robot tool was the most accurate. In the pipe-welding task, the quality of weld was the best in terms of measured tool-trajectory smoothness and visual weld observation.","PeriodicalId":54942,"journal":{"name":"International Journal of Robotics Research","volume":null,"pages":null},"PeriodicalIF":9.2,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43716509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-01DOI: 10.1177/02783649221102473
Marko Bjelonic, R. Grandia, Moritz Geilinger, Oliver Harley, V. S. Medeiros, Vuk Pajovic, E. Jelavic, Stelian Coros, M. Hutter
We describe an optimization-based framework to perform complex locomotion skills for robots with legs and wheels. The generation of complex motions over a long-time horizon often requires offline computation due to current computing constraints and is mostly accomplished through trajectory optimization (TO). In contrast, model predictive control (MPC) focuses on the online computation of trajectories, robust even in the presence of uncertainty, albeit mostly over shorter time horizons and is prone to generating nonoptimal solutions over the horizon of the task’s goals. Our article’s contributions overcome this trade-off by combining offline motion libraries and online MPC, uniting a complex, long-time horizon plan with reactive, short-time horizon solutions. We start from offline trajectories that can be, for example, generated by TO or sampling-based methods. Also, multiple offline trajectories can be composed out of a motion library into a single maneuver. We then use these offline trajectories as the cost for the online MPC, allowing us to smoothly blend between multiple composed motions even in the presence of discontinuous transitions. The MPC optimizes from the measured state, resulting in feedback control, which robustifies the task’s execution by reacting to disturbances and looking ahead at the offline trajectory. With our contribution, motion designers can choose their favorite method to iterate over behavior designs offline without tuning robot experiments, enabling them to author new behaviors rapidly. Our experiments demonstrate complex and dynamic motions on our traditional quadrupedal robot ANYmal and its roller-walking version. Moreover, the article’s findings contribute to evaluating five planning algorithms.
{"title":"Offline motion libraries and online MPC for advanced mobility skills","authors":"Marko Bjelonic, R. Grandia, Moritz Geilinger, Oliver Harley, V. S. Medeiros, Vuk Pajovic, E. Jelavic, Stelian Coros, M. Hutter","doi":"10.1177/02783649221102473","DOIUrl":"https://doi.org/10.1177/02783649221102473","url":null,"abstract":"We describe an optimization-based framework to perform complex locomotion skills for robots with legs and wheels. The generation of complex motions over a long-time horizon often requires offline computation due to current computing constraints and is mostly accomplished through trajectory optimization (TO). In contrast, model predictive control (MPC) focuses on the online computation of trajectories, robust even in the presence of uncertainty, albeit mostly over shorter time horizons and is prone to generating nonoptimal solutions over the horizon of the task’s goals. Our article’s contributions overcome this trade-off by combining offline motion libraries and online MPC, uniting a complex, long-time horizon plan with reactive, short-time horizon solutions. We start from offline trajectories that can be, for example, generated by TO or sampling-based methods. Also, multiple offline trajectories can be composed out of a motion library into a single maneuver. We then use these offline trajectories as the cost for the online MPC, allowing us to smoothly blend between multiple composed motions even in the presence of discontinuous transitions. The MPC optimizes from the measured state, resulting in feedback control, which robustifies the task’s execution by reacting to disturbances and looking ahead at the offline trajectory. With our contribution, motion designers can choose their favorite method to iterate over behavior designs offline without tuning robot experiments, enabling them to author new behaviors rapidly. Our experiments demonstrate complex and dynamic motions on our traditional quadrupedal robot ANYmal and its roller-walking version. Moreover, the article’s findings contribute to evaluating five planning algorithms.","PeriodicalId":54942,"journal":{"name":"International Journal of Robotics Research","volume":null,"pages":null},"PeriodicalIF":9.2,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46097484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","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：