Efficient planning with the Bayes tree for active SLAM

Chaves, Stephen; Eustice, Ryan M.

doi:10.1109/iros.2016.7759686

Cited by 17 publications

(20 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Approaches that focus on autnomous navigation problems, such as active SLAM, have been also widely examined (e.g. Stachniss et al 2004;Bryson and Sukkarieh 2008;Du et al 2011;Kim and Eustice 2014;Chaves and Eustice 2016;Kopitkov and Indelman 2017).…”

Section: Related Workmentioning

confidence: 99%

Fast Action Elimination for Efficient Decision Making and Belief Space Planning Using Bounded Approximations

Elimelech

Indelman

2019

Springer Proceedings in Advanced Robotics

View full text Add to dashboard Cite

In this work, we introduce a new approach for the efficient solution of autonomous decision and planning problems, with a special focus on decision making under uncertainty and belief space planning (BSP) in high-dimensional state spaces. Usually, to solve the decision problem, we identify the optimal action, according to some objective function. Instead, we claim that we can sometimes generate and solve an analogous yet simplified decision problem, which can be solved more efficiently. Furthermore, a wise simplification method can lead to the same action selection, or one for which the maximal loss can be guaranteed. This simplification is separated from the state inference, and does not compromise its accuracy, as the selected action would finally be applied on the original state. At first, we develop the concept for general decision problems, and provide a theoretical framework of definitions to allow a coherent discussion. We then practically apply these ideas to BSP problems, in which the problem is simplified by considering a sparse approximation of the initial belief. The scalable sparsification algorithm we provide is able to yield solutions which are guaranteed to be consistent with the original problem. We demonstrate the benefits of the approach in the solution of a highly realistic active-SLAM problem, and manage to significantly reduce computation time, with practically no loss in the quality of solution. This rigorous and fundamental work is conceptually novel, and holds numerous possible extensions.

show abstract

Section: Related Workmentioning

confidence: 99%

Fast Action Elimination for Efficient Decision Making and Belief Space Planning Using Bounded Approximations

Elimelech

Indelman

2019

Springer Proceedings in Advanced Robotics

View full text Add to dashboard Cite

show abstract

“…Yet, in most BSP approaches, including our own rAMDL approach, the similarity between candidate actions is not exploited and each candidate is evaluated from scratch. To the best of our knowledge, only the work by Chaves et al (Chaves and Eustice, 2016) was done in this direction. Their approach performs fast explicit inference over the posterior belief, by constraining variable ordering of the Bayes tree data structure to have candidates' common variables eliminated first.…”

Section: Belief Space Planningmentioning

confidence: 99%

“…It explicitly calculates the posterior belief for each action, and though this calculation is done fast, the method still requires additional memory to store such posterior beliefs. Further, the approach in Chaves and Eustice (2016) does not deal with information-theoretic objective functions whose runtime complexity is usually very expensive, as mentioned above. Moreover, it can only be applied when the SLAM algorithm is implemented using a Bayes tree (Kaess et al, 2012), and it was shown to work only for the case where actions are trajectories constrained to have only a single common part.…”

Section: Related Workmentioning

confidence: 99%

General-purpose incremental covariance update and efficient belief space planning via a factor-graph propagation action tree

Kopitkov

Indelman

2019

The International Journal of Robotics Research

View full text Add to dashboard Cite

Fast covariance calculation is required both for SLAM (e.g. in order to solve data association) and for evaluating the information-theoretic term for different candidate actions in belief space planning (BSP). In this paper we make two primary contributions. First, we develop a novel general-purpose incremental covariance update technique, which efficiently recovers specific covariance entries after any change in the inference problem, such as introduction of new observations/variables or re-linearization of the state vector. Our approach is shown to recover them faster than other state-of-the-art methods. Second, we present a computationally efficient approach for BSP in high-dimensional state spaces, leveraging our incremental covariance update method. State of the art BSP approaches perform belief propagation for each candidate action and then evaluate an objective function that typically includes an information-theoretic term, such as entropy or information gain. Yet, candidate actions often have similar parts (e.g. common trajectory parts), which are however evaluated separately for each candidate. Moreover, calculating the information-theoretic term involves a costly determinant computation of the entire information (covariance) matrix which is O(n 3 ) with n being dimension of the state or costly Schur complement operations if only marginal posterior covariance of certain variables is of interest. Our approach, rAMDL-Tree, extends our previous BSP method rAMDL (Kopitkov and Indelman, 2017), by exploiting incremental covariance calculation and performing calculation re-use between common parts of non-myopic candidate actions, such that these parts are evaluated only once, in contrast to existing approaches. To that end, we represent all candidate actions together in a single unified graphical model, which we introduce and call a factor-graph propagation (FGP) action tree. Each arrow (edge) of the FGP action tree represents a sub-action of one (or more) candidate action sequence and in order to evaluate its information impact we require specific covariance entries of an intermediate belief represented by tree's vertex from which the edge is coming out (e.g. tail of the arrow). Overall, our approach has only a one-time calculation that depends on n, while evaluating action impact does not depend on n. We perform a careful examination of our approaches in simulation, considering the problem of autonomous navigation in unknown environments, where rAMDL-Tree shows superior performance compared to rAMDL, while determining the same best actions.Then, the IG of each sub-action is equal to:and sum of these IGs is equal to:

show abstract

“…The second one is to develop a method to explore the necessary terrain conditions by only using few vision sensors information. Laser range sensors are useful to obtain terrain information and robot position, which is called simultaneous localization and mapping (SLAM) system [12][13][14]. SLAM systems can describe the positional and simple postural relationship between the whole robot (robot body) and environment.…”

Section: • Mobility In Unknown (Low-visibility) Environmentmentioning

confidence: 99%

Compound locomotion control system combining crawling and walking for multi-crawler multi-arm robot to adapt unstructured and unknown terrain

et al. 2018

View full text Add to dashboard Cite

How to improve task performance and how to control a robot in extreme environments when just a few sensors can be used to obtain environmental information are two of the problems for disaster response robots (DRRs). Compared with conventional DRRs, multi-arm multi-flipper crawler type robot (MAMFR) have high mobility and task-execution capabilities. Because, crawler robots and quadruped robots have complementary advantages in locomotion, therefore we have the vision to combine both of these advantages in MAMFR. Usually, MAMFR (like four-arm four-flipper robot OCTOPUS) was designed for working in extreme environments such as that with heavy smoke and fog. Therefore it is a quite necessary requirement that DRR should have the ability to work in the situation even if vision and laser sensors are not available. To maximize terrains adaption ability, self-balancing capability, and obstacle getting over capability in unstructured disaster site, as well as reduce the difficulty of robot control, we proposed a semi-autonomous control system to realize this compound locomotion method for MAMFRs. In this control strategy, robot can explore the terrain and obtain basic information about the surrounding by its structure and internal sensors, such as encoder and inertial measurement unit. Except that control system also can recognize the relative positional relationship between robot and surrounding environment through its arms and crawlers state when robot moving. Because the control rules is simple but effective, and each part can adjust its own state automatically according to robot state and explored terrain, MRMFRs have better terrain adaptability and stability. Experimental results with a virtual reality simulator indicated that the designed control system significantly improved stability and mobility of robot in tasks, it also indicated that robot can adapt complex terrain when controlled by designed control system.

show abstract

Efficient planning with the Bayes tree for active SLAM

Cited by 17 publications

References 25 publications

Fast Action Elimination for Efficient Decision Making and Belief Space Planning Using Bounded Approximations

Fast Action Elimination for Efficient Decision Making and Belief Space Planning Using Bounded Approximations

General-purpose incremental covariance update and efficient belief space planning via a factor-graph propagation action tree

Compound locomotion control system combining crawling and walking for multi-crawler multi-arm robot to adapt unstructured and unknown terrain

Contact Info

Product

Resources

About