“…Finally, these methods can be utilized as a baseline for more complex (not purely uphill and respecting other objectives) behavior planning, as in (Johnson et al, 2016).…”
Section: Immediate Assessment and Near Term Extensionsmentioning
This paper reports on autonomous ascent by a legged robotic platform in outdoor forested terrain. Two controllers govern the integration of online Inertial Measurement Unit (IMU) and Light Detection And Ranging (LIDAR) sensor signals into commands for climbing by means of an abstracted (unicycle) representation of the platform in support of different performance goals: a kinematic version for endurance and a dynamic version for speed. These control laws, backed by a suite of formal correctness guarantees, encourage a stripped down sensory suite supporting a simplified world model whose departures from the actual physical environment are handled by the mechanical competence of the legged platform. Both behaviors are implemented on a version of the legged RHex platform, and experiments spanning almost a kilometer (thousands of body lengths) in various challenging settings are conducted.
“…Finally, these methods can be utilized as a baseline for more complex (not purely uphill and respecting other objectives) behavior planning, as in (Johnson et al, 2016).…”
Section: Immediate Assessment and Near Term Extensionsmentioning
This paper reports on autonomous ascent by a legged robotic platform in outdoor forested terrain. Two controllers govern the integration of online Inertial Measurement Unit (IMU) and Light Detection And Ranging (LIDAR) sensor signals into commands for climbing by means of an abstracted (unicycle) representation of the platform in support of different performance goals: a kinematic version for endurance and a dynamic version for speed. These control laws, backed by a suite of formal correctness guarantees, encourage a stripped down sensory suite supporting a simplified world model whose departures from the actual physical environment are handled by the mechanical competence of the legged platform. Both behaviors are implemented on a version of the legged RHex platform, and experiments spanning almost a kilometer (thousands of body lengths) in various challenging settings are conducted.
“…Uncertainty is inevitable during non-prehensile manipulation Yu et al [12]. One approach to handling uncertainty is through actions that funnel uncertainty to the goal state(s) [6], [13]- [15]. Uncertainty is also tackled through using sensor feedback during manipulation.…”
This work is published as a conference paper [1] at IEEE Humanoids 2018.We consider the problem of grasping in clutter. While there have been motion planners developed to address this problem in recent years, these planners are mostly tailored for openloop execution. Open-loop execution in this domain, however, is likely to fail, since it is not possible to model the dynamics of the multi-body multi-contact physical system with enough accuracy, neither is it reasonable to expect robots to know the exact physical properties of objects, such as frictional, inertial, and geometrical. Therefore, we propose an online re-planning approach for grasping through clutter. The main challenge is the long planning times this domain requires, which makes fast re-planning and fluent execution difficult to realize. In order to address this, we propose an easily parallelizable stochastic trajectory optimization based algorithm that generates a sequence of optimal controls. We show that by running this optimizer only for a small number of iterations, it is possible to perform real time re-planning cycles to achieve reactive manipulation under clutter and uncertainty.
“…There has been significant recent interest in non-prehensile pushing-based manipulation. Most existing work use motion planning and open-loop execution to address the problem of generating a sequence of actions to complete a non-prehensile manipulation task [16,17,7,23,11]. Others developed closed-loop approaches.…”
We propose a planning and control approach to physics-based manipulation. The key feature of the algorithm is that it can adapt to the accuracy requirements of a task, by slowing down and generating "careful" motion when the task requires high accuracy, and by speeding up and moving fast when the task tolerates inaccuracy. We formulate the problem as an MDP with action-dependent stochasticity and propose an approximate online solution to it. We use a trajectory optimizer with a deterministic model to suggest promising actions to the MDP, to reduce computation time spent on evaluating different actions. We conducted experiments in simulation and on a real robotic system. Our results show that with a task-adaptive planning and control approach, a robot can choose fast or slow actions depending on the task accuracy and uncertainty level. The robot makes these decisions online and is able to maintain high success rates while completing manipulation tasks as fast as possible.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.