Journal Article•
IEEE International Conference on Robotics and Automation (ICRA) におけるフルードパワー技術の研究動向
About: This article is published in TRANSACTIONS OF THE JAPAN FLUID POWER SYSTEM SOCIETY.The article was published on 2011-09-15 and is currently open access. It has received 351 citations till now.
Citations
More filters
TL;DR: This work forms a rigorously probabilistic cost function that combines reprojection errors of landmarks and inertial terms and compares the performance to an implementation of a state-of-the-art stochastic cloning sliding-window filter.
Abstract: Combining visual and inertial measurements has become popular in mobile robotics, since the two sensing modalities offer complementary characteristics that make them the ideal choice for accurate visual-inertial odometry or simultaneous localization and mapping SLAM. While historically the problem has been addressed with filtering, advancements in visual estimation suggest that nonlinear optimization offers superior accuracy, while still tractable in complexity thanks to the sparsity of the underlying problem. Taking inspiration from these findings, we formulate a rigorously probabilistic cost function that combines reprojection errors of landmarks and inertial terms. The problem is kept tractable and thus ensuring real-time operation by limiting the optimization to a bounded window of keyframes through marginalization. Keyframes may be spaced in time by arbitrary intervals, while still related by linearized inertial terms. We present evaluation results on complementary datasets recorded with our custom-built stereo visual-inertial hardware that accurately synchronizes accelerometer and gyroscope measurements with imagery. A comparison of both a stereo and monocular version of our algorithm with and without online extrinsics estimation is shown with respect to ground truth. Furthermore, we compare the performance to an implementation of a state-of-the-art stochastic cloning sliding-window filter. This competitive reference implementation performs tightly coupled filtering-based visual-inertial odometry. While our approach declaredly demands more computation, we show its superior performance in terms of accuracy.
1,472 citations
Cites methods from "IEEE International Conference on Ro..."
...The custom-built visual– inertial sensor is described in detail by Nikolic et al. (2014)....
[...]
TL;DR: An intelligent trial-and-error algorithm is introduced that allows robots to adapt to damage in less than two minutes in large search spaces without requiring self-diagnosis or pre-specified contingency plans, and may shed light on the principles that animals use to adaptation to injury.
Abstract: An intelligent trial-and-error learning algorithm is presented that allows robots to adapt in minutes to compensate for a wide variety of types of damage. Autonomous mobile robots would be extremely useful in remote or hostile environments such as space, deep oceans or disaster areas. An outstanding challenge is to make such robots able to recover after damage. Jean-Baptiste Mouret and colleagues have developed a machine learning algorithm that enables damaged robots to quickly regain their ability to perform tasks. When they sustain damage — such as broken or even missing legs — the robots adopt an intelligent trial-and-error approach, trying out possible behaviours that they calculate to be potentially high-performing. After a handful of such experiments they discover, in less than two minutes, a compensatory behaviour that works in spite of the damage. Robots have transformed many industries, most notably manufacturing1, and have the power to deliver tremendous benefits to society, such as in search and rescue2, disaster response3, health care4 and transportation5. They are also invaluable tools for scientific exploration in environments inaccessible to humans, from distant planets6 to deep oceans7. A major obstacle to their widespread adoption in more complex environments outside factories is their fragility6,8. Whereas animals can quickly adapt to injuries, current robots cannot ‘think outside the box’ to find a compensatory behaviour when they are damaged: they are limited to their pre-specified self-sensing abilities, can diagnose only anticipated failure modes9, and require a pre-programmed contingency plan for every type of potential damage, an impracticality for complex robots6,8. A promising approach to reducing robot fragility involves having robots learn appropriate behaviours in response to damage10,11, but current techniques are slow even with small, constrained search spaces12. Here we introduce an intelligent trial-and-error algorithm that allows robots to adapt to damage in less than two minutes in large search spaces without requiring self-diagnosis or pre-specified contingency plans. Before the robot is deployed, it uses a novel technique to create a detailed map of the space of high-performing behaviours. This map represents the robot’s prior knowledge about what behaviours it can perform and their value. When the robot is damaged, it uses this prior knowledge to guide a trial-and-error learning algorithm that conducts intelligent experiments to rapidly discover a behaviour that compensates for the damage. Experiments reveal successful adaptations for a legged robot injured in five different ways, including damaged, broken, and missing legs, and for a robotic arm with joints broken in 14 different ways. This new algorithm will enable more robust, effective, autonomous robots, and may shed light on the principles that animals use to adapt to injury.
928 citations
Cites background from "IEEE International Conference on Ro..."
...Some variants (4 and 5) correspond to state-of-the-art learning algorithms (policy gradient: Kohl et al. 2004; Bayesian optimization: Lizotte et al. 2007, Tesch et al., 2011, Calandra et al. 2014,)....
[...]
TL;DR: This work presents a novel solution, named RR-GP, which builds a learned motion pattern model by combining the flexibility of Gaussian processes (GP) with the efficiency of RRT-Reach, a sampling-based reachability computation.
Abstract: This paper presents a real-time path planning algorithm that guarantees probabilistic feasibility for autonomous robots with uncertain dynamics operating amidst one or more dynamic obstacles with uncertain motion patterns. Planning safe trajectories under such conditions requires both accurate prediction and proper integration of future obstacle behavior within the planner. Given that available observation data is limited, the motion model must provide generalizable predictions that satisfy dynamic and environmental constraints, a limitation of existing approaches. This work presents a novel solution, named RR-GP, which builds a learned motion pattern model by combining the flexibility of Gaussian processes (GP) with the efficiency of RRT-Reach, a sampling-based reachability computation. Obstacle trajectory GP predictions are conditioned on dynamically feasible paths identified from the reachability analysis, yielding more accurate predictions of future behavior. RR-GP predictions are integrated with a robust path planner, using chance-constrained RRT, to identify probabilistically feasible paths. Theoretical guarantees of probabilistic feasibility are shown for linear systems under Gaussian uncertainty; approximations for nonlinear dynamics and/or non-Gaussian uncertainty are also presented. Simulations demonstrate that, with this planner, an autonomous vehicle can safely navigate a complex environment in real-time while significantly reducing the risk of collisions with dynamic obstacles.
265 citations
Cites methods from "IEEE International Conference on Ro..."
...Althoff et al. (2011) use Monte Carlo sampling to estimate inevitable collision states probabilistically, while Henry et al. (2010) apply inverse reinforcement learning for human-like behavior....
[...]
01 Jun 2013
TL;DR: This work proposes a fundamentally different approach: allow richer error models that allow the probability of a failure to be explicitly modeled, and shows that the proposed method not only allows loop closing errors to be automatically identified, but also that in extreme cases the “front-end” loop-validation systems can be unnecessary.
Abstract: The central challenge in robotic mapping is obtaining reliable data associations (or "loop closures"): state-of-the-art inference algorithms can fail catastrophically if even one erroneous loop closure is incorporated into the map. Consequently, much work has been done to push error rates closer to zero. However, a long-lived or multi-robot system will still encounter errors, leading to system failure. We propose a fundamentally different approach: allow richer error models that allow the probability of a failure to be explicitly modeled. In other words, rather than characterizing loop closures as being "right" or "wrong", we propose characterizing the error of those loop closures in a more expressive manner that can account for their non-Gaussian behavior. Our approach leads to an fully integrated Bayesian framework for dealing with error-prone data. Unlike earlier multiple-hypothesis approaches, our approach avoids exponential memory complexity and is fast enough for real-time performance. We show that the proposed method not only allows loop closing errors to be automatically identified, but also that in extreme cases, the "front-end" loop-validation systems can be unnecessary. We demonstrate our system both on standard benchmarks and on the real-world data sets that motivated this work.
260 citations
TL;DR: The paper-based keypad detects the change in capacitance associated with the touch of a finger to one of its buttons and requires the appropriate sequence of touches to disarm the system.
Abstract: This paper describes low-cost, thin, and pliable touch pads constructed from a commercially available, metallized paper commonly used as packaging material for beverages and book covers. The associated electronics with the individual keys in the touch pads detect changes in capacitance or contact with fi ngers by using the effective capacitance of the human body and the electrical impedance across the tip of a fi nger. To create the individual keys, a laser cutter ablates lines through the fi lm of evaporated aluminum on the metallized paper to pattern distinct, conductive regions. This work includes the experimental characterization of two types of capacitive buttons and illustrates their use with applications in a keypad with 10 individually addressable keys , a keypad that conforms to a cube, and a keypad on an alarmed cardboard box. With their easily arrayed keys, environmentally benign material, and low cost, the touch pads have the potential to contribute to future developments in disposable, fl exible electronics, active, “smart” packaging, user interfaces for biomedical instrumentation, biomedical devices for the developing world, applications for monitoring animal and plant health, food and water quality, and disposable games (e.g., providers of content for consumer products). There is no simple method of integrating buttons with structures on single-use or throw-away devices. Current commercial buttons are not thin enough, inexpensive enough, or easy enough to array seamlessly with paper-based products for disposable applications. The touch pads in this work are thin ( ∼ 60 μ m in some cases), simple to array, fabricated by etching patterns into metallized paper, low-cost ( < $0.25 m − 2 for the thin grade of metallized paper we use in this work), and lightweight
184 citations
References
More filters
TL;DR: This work forms a rigorously probabilistic cost function that combines reprojection errors of landmarks and inertial terms and compares the performance to an implementation of a state-of-the-art stochastic cloning sliding-window filter.
Abstract: Combining visual and inertial measurements has become popular in mobile robotics, since the two sensing modalities offer complementary characteristics that make them the ideal choice for accurate visual-inertial odometry or simultaneous localization and mapping SLAM. While historically the problem has been addressed with filtering, advancements in visual estimation suggest that nonlinear optimization offers superior accuracy, while still tractable in complexity thanks to the sparsity of the underlying problem. Taking inspiration from these findings, we formulate a rigorously probabilistic cost function that combines reprojection errors of landmarks and inertial terms. The problem is kept tractable and thus ensuring real-time operation by limiting the optimization to a bounded window of keyframes through marginalization. Keyframes may be spaced in time by arbitrary intervals, while still related by linearized inertial terms. We present evaluation results on complementary datasets recorded with our custom-built stereo visual-inertial hardware that accurately synchronizes accelerometer and gyroscope measurements with imagery. A comparison of both a stereo and monocular version of our algorithm with and without online extrinsics estimation is shown with respect to ground truth. Furthermore, we compare the performance to an implementation of a state-of-the-art stochastic cloning sliding-window filter. This competitive reference implementation performs tightly coupled filtering-based visual-inertial odometry. While our approach declaredly demands more computation, we show its superior performance in terms of accuracy.
1,472 citations
TL;DR: An intelligent trial-and-error algorithm is introduced that allows robots to adapt to damage in less than two minutes in large search spaces without requiring self-diagnosis or pre-specified contingency plans, and may shed light on the principles that animals use to adaptation to injury.
Abstract: An intelligent trial-and-error learning algorithm is presented that allows robots to adapt in minutes to compensate for a wide variety of types of damage. Autonomous mobile robots would be extremely useful in remote or hostile environments such as space, deep oceans or disaster areas. An outstanding challenge is to make such robots able to recover after damage. Jean-Baptiste Mouret and colleagues have developed a machine learning algorithm that enables damaged robots to quickly regain their ability to perform tasks. When they sustain damage — such as broken or even missing legs — the robots adopt an intelligent trial-and-error approach, trying out possible behaviours that they calculate to be potentially high-performing. After a handful of such experiments they discover, in less than two minutes, a compensatory behaviour that works in spite of the damage. Robots have transformed many industries, most notably manufacturing1, and have the power to deliver tremendous benefits to society, such as in search and rescue2, disaster response3, health care4 and transportation5. They are also invaluable tools for scientific exploration in environments inaccessible to humans, from distant planets6 to deep oceans7. A major obstacle to their widespread adoption in more complex environments outside factories is their fragility6,8. Whereas animals can quickly adapt to injuries, current robots cannot ‘think outside the box’ to find a compensatory behaviour when they are damaged: they are limited to their pre-specified self-sensing abilities, can diagnose only anticipated failure modes9, and require a pre-programmed contingency plan for every type of potential damage, an impracticality for complex robots6,8. A promising approach to reducing robot fragility involves having robots learn appropriate behaviours in response to damage10,11, but current techniques are slow even with small, constrained search spaces12. Here we introduce an intelligent trial-and-error algorithm that allows robots to adapt to damage in less than two minutes in large search spaces without requiring self-diagnosis or pre-specified contingency plans. Before the robot is deployed, it uses a novel technique to create a detailed map of the space of high-performing behaviours. This map represents the robot’s prior knowledge about what behaviours it can perform and their value. When the robot is damaged, it uses this prior knowledge to guide a trial-and-error learning algorithm that conducts intelligent experiments to rapidly discover a behaviour that compensates for the damage. Experiments reveal successful adaptations for a legged robot injured in five different ways, including damaged, broken, and missing legs, and for a robotic arm with joints broken in 14 different ways. This new algorithm will enable more robust, effective, autonomous robots, and may shed light on the principles that animals use to adapt to injury.
928 citations
TL;DR: This work presents a novel solution, named RR-GP, which builds a learned motion pattern model by combining the flexibility of Gaussian processes (GP) with the efficiency of RRT-Reach, a sampling-based reachability computation.
Abstract: This paper presents a real-time path planning algorithm that guarantees probabilistic feasibility for autonomous robots with uncertain dynamics operating amidst one or more dynamic obstacles with uncertain motion patterns. Planning safe trajectories under such conditions requires both accurate prediction and proper integration of future obstacle behavior within the planner. Given that available observation data is limited, the motion model must provide generalizable predictions that satisfy dynamic and environmental constraints, a limitation of existing approaches. This work presents a novel solution, named RR-GP, which builds a learned motion pattern model by combining the flexibility of Gaussian processes (GP) with the efficiency of RRT-Reach, a sampling-based reachability computation. Obstacle trajectory GP predictions are conditioned on dynamically feasible paths identified from the reachability analysis, yielding more accurate predictions of future behavior. RR-GP predictions are integrated with a robust path planner, using chance-constrained RRT, to identify probabilistically feasible paths. Theoretical guarantees of probabilistic feasibility are shown for linear systems under Gaussian uncertainty; approximations for nonlinear dynamics and/or non-Gaussian uncertainty are also presented. Simulations demonstrate that, with this planner, an autonomous vehicle can safely navigate a complex environment in real-time while significantly reducing the risk of collisions with dynamic obstacles.
265 citations
01 Jun 2013
TL;DR: This work proposes a fundamentally different approach: allow richer error models that allow the probability of a failure to be explicitly modeled, and shows that the proposed method not only allows loop closing errors to be automatically identified, but also that in extreme cases the “front-end” loop-validation systems can be unnecessary.
Abstract: The central challenge in robotic mapping is obtaining reliable data associations (or "loop closures"): state-of-the-art inference algorithms can fail catastrophically if even one erroneous loop closure is incorporated into the map. Consequently, much work has been done to push error rates closer to zero. However, a long-lived or multi-robot system will still encounter errors, leading to system failure. We propose a fundamentally different approach: allow richer error models that allow the probability of a failure to be explicitly modeled. In other words, rather than characterizing loop closures as being "right" or "wrong", we propose characterizing the error of those loop closures in a more expressive manner that can account for their non-Gaussian behavior. Our approach leads to an fully integrated Bayesian framework for dealing with error-prone data. Unlike earlier multiple-hypothesis approaches, our approach avoids exponential memory complexity and is fast enough for real-time performance. We show that the proposed method not only allows loop closing errors to be automatically identified, but also that in extreme cases, the "front-end" loop-validation systems can be unnecessary. We demonstrate our system both on standard benchmarks and on the real-world data sets that motivated this work.
260 citations
TL;DR: In this paper, a dataset of images containing fruits is introduced and a neural network is trained to detect fruits. But the authors discuss the reason why they chose to use fruits in this project by proposing a few applications that could use this kind of neural network.
Abstract: In this paper we introduce a new, high-quality, dataset of images containing fruits. We also present the results of some numerical experiment for training a neural network to detect fruits. We discuss the reason why we chose to use fruits in this project by proposing a few applications that could use this kind of neural network.
237 citations