Abstract:Abstract-Path planning in dynamic environments with moving obstacles is computationally complex since it requires modeling time as an additional dimension. While in other domains there are state dominance relationships that can significantly reduce the complexity of the search, in dynamic environments such relationships do not exist. This paper presents a novel state dominance relationship tailored specifically for dynamic environments, and presents a planner that uses that property to plan paths over ten time… Show more
Section: Challenges Of Human-aware Navigationmentioning
confidence: 99%
“…The temporal dimension in that work is segmented into safe and unsafe intervals instead of regularly discretized time, reducing the search space expansion. Gonzalez et al [28] enhance that idea allowing for continous cost functions as well, a prerequisite to apply social cost functions to search.…”
Section: Temporal Planningmentioning
confidence: 99%
“…Behavior Selection [1,17,19,27,30,33,34,35,43,56,79,69,70,81] 14 Global Planning [6,7,21,28,30,37,38,43,44,48,49,50,54,56,57,59,60,62,65,69,70,71,83,84,87,88,89,90,91,92,97,104,106]…”
Navigation is a basic skill for autonomous robots. In the last years human-robot interaction has become an important research field that spans all of the robot capabilities including perception, reasoning, learning, manipulation and navigation. For navigation, the presence of humans requires novel approaches that take into account the constraints of human comfort as well as social rules. Besides these constraints, putting robots among humans opens new interaction possibilities for robots, also for navigation tasks, such as robot guides. This paper provides a survey of existing approaches to human-aware navigation and offers a general classification scheme for the presented methods.
Section: Challenges Of Human-aware Navigationmentioning
confidence: 99%
“…The temporal dimension in that work is segmented into safe and unsafe intervals instead of regularly discretized time, reducing the search space expansion. Gonzalez et al [28] enhance that idea allowing for continous cost functions as well, a prerequisite to apply social cost functions to search.…”
Section: Temporal Planningmentioning
confidence: 99%
“…Behavior Selection [1,17,19,27,30,33,34,35,43,56,79,69,70,81] 14 Global Planning [6,7,21,28,30,37,38,43,44,48,49,50,54,56,57,59,60,62,65,69,70,71,83,84,87,88,89,90,91,92,97,104,106]…”
Navigation is a basic skill for autonomous robots. In the last years human-robot interaction has become an important research field that spans all of the robot capabilities including perception, reasoning, learning, manipulation and navigation. For navigation, the presence of humans requires novel approaches that take into account the constraints of human comfort as well as social rules. Besides these constraints, putting robots among humans opens new interaction possibilities for robots, also for navigation tasks, such as robot guides. This paper provides a survey of existing approaches to human-aware navigation and offers a general classification scheme for the presented methods.
“…Early works explored control sampling approaches [240], and recent state sampling works have made model simplifications to handle the differential constraints in an online manner, such as keeping to a constant ego robot speed [251]. Others have performed planning by graph search over a discrete, time-bounded lattice structure built from motion primitives [252], or a grid cell decomposition of the state space [253], though these methods loose the benefits of sampling based approaches (which are less limited in resolution, and have potential for rewiring and optimization).…”
Section: Planning Subject To Differential Constraintsmentioning
Autonomous vehicles are expected to play a key role in the future of urban transportation systems, as they offer potential for additional safety, increased productivity, greater accessibility, better road efficiency, and positive impact on the environment. Research in autonomous systems has seen dramatic advances in recent years, due to the increases in available computing power and reduced cost in sensing and computing technologies, resulting in maturing technological readiness level of fully autonomous vehicles. The objective of this paper is to provide a general overview of the recent developments in the realm of autonomous vehicle software systems. Fundamental components of autonomous vehicle software are reviewed, and recent developments in each area are discussed.
“…Therefore, it is mandatory to constrain the path searches only to high priority space during pathfinding to effectively resolve the efficiency and optimality trade-off. Various approaches have been proposed to speed-up the path computations, such as hierarchical abstractions [42][43][44], symmetry breaking [45,46], jump point search [47][48][49][50], sub-goal graphs [51], compressed path databases [52,53], accurate heuristics [54], swamp hierarchies [55], pruning dominant states [56], influence-aware pathfinders [57], and constraints-aware navigation (CAN) [58]. Despite the success of such enhancements, in most cases, either many locations of the maps are searched needlessly, or path length degrades.…”
This paper proposes a new flight path planning algorithm that finds collision-free, optimal/near-optimal and flyable paths for unmanned aerial vehicles (UAVs) in three-dimensional (3D) environments with fixed obstacles. The proposed algorithm significantly reduces pathfinding computing time without significantly degrading path lengths by using space circumscription and a sparse visibility graph in the pathfinding process. We devise a novel method by exploiting the information about obstacle geometry to circumscribe the search space in the form of a half cylinder from which a working path for UAV can be computed without sacrificing the guarantees on near-optimality and speed. Furthermore, we generate a sparse visibility graph from the circumscribed space and find the initial path, which is subsequently optimized. The proposed algorithm effectively resolves the efficiency and optimality trade-off by searching the path only from the high priority circumscribed space of a map. The simulation results obtained from various maps, and comparison with the existing methods show the effectiveness of the proposed algorithm and verify the aforementioned claims.
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.