Results 1 - 10
of
39
Autonomous obstacle avoidance and maneuvering on a vision-guided mav using on-board processing
- In Proc. of the IEEE Int. Conf. on Robotics and Automation (ICRA
, 2011
"... Abstract — We present a novel stereo-based obstacle avoid-ance system on a vision-guided micro air vehicle (MAV) that is capable of fully autonomous maneuvers in unknown and dynamic environments. All algorithms run exclusively on the vehicle’s on-board computer, and at high frequencies that allow th ..."
Abstract
-
Cited by 15 (7 self)
- Add to MetaCart
(Show Context)
Abstract — We present a novel stereo-based obstacle avoid-ance system on a vision-guided micro air vehicle (MAV) that is capable of fully autonomous maneuvers in unknown and dynamic environments. All algorithms run exclusively on the vehicle’s on-board computer, and at high frequencies that allow the MAV to react quickly to obstacles appearing in its flight trajectory. Our MAV platform is a quadrotor aircraft equipped with an inertial measurement unit and two stereo rigs. An obstacle mapping algorithm processes stereo images, producing a 3D map representation of the environment; at the same time, a dynamic anytime path planner plans a collision-free path to a goal point. I.
Safe distributed motion coordination for second-order systems with different planning cycles
- INTL J. OF ROBOTICS RESEARCH
, 2012
"... When multiple robots operate in the same environment, it is desirable for scalability purposes to coordinate their motion in a distributed fashion while providing guarantees about their safety. If the robots have to respect second-order dynamics, this becomes a challenging problem, even for static e ..."
Abstract
-
Cited by 10 (4 self)
- Add to MetaCart
(Show Context)
When multiple robots operate in the same environment, it is desirable for scalability purposes to coordinate their motion in a distributed fashion while providing guarantees about their safety. If the robots have to respect second-order dynamics, this becomes a challenging problem, even for static environments. This work presents a replanning framework where each robot computes partial plans during each cycle, while executing a previously computed trajectory. Each robot communicates with its neighbors to select a trajectory that is safe over an infinite time horizon. The proposed approach does not require synchronization and allows the robots to dynamically change their cycles over time. This paper proves that the proposed motion coordination algorithm guarantees safety under this general setting. This framework is not specific to the underlying robot dynamics, as it can be used with a variety of dynamical systems, nor to the planning or control algorithm used to generate the robot trajectories. The performance of the approach is evaluated using a distributed multi-robot simulator on a computing cluster, where the simulated robots are forced to communicate by exchanging messages. The simulation results confirm the safety of the algorithm in various environments with up to 32 robots governed by second-order dynamics.
Toward automated driving in cities using closeto-market sensors: An overview of the v-charge project
- In IEEE Intelligent Vehicles Symposium (IV), 2013. doi: 10.1109/IVS.2013.6629566. URL http://ieeexplore.ieee. org/xpls/abs all.jsp?arnumber=6629566
"... Abstract—Future requirements for drastic reduction of CO2 production and energy consumption will lead to significant changes in the way we see mobility in the years to come. However, the automotive industry has identified significant barriers to the adoption of electric vehicles, including reduced d ..."
Abstract
-
Cited by 8 (6 self)
- Add to MetaCart
(Show Context)
Abstract—Future requirements for drastic reduction of CO2 production and energy consumption will lead to significant changes in the way we see mobility in the years to come. However, the automotive industry has identified significant barriers to the adoption of electric vehicles, including reduced driving range and greatly increased refueling times. Automated cars have the potential to reduce the environ-mental impact of driving, and increase the safety of motor vehicle travel. The current state-of-the-art in vehicle automation requires a suite of expensive sensors. While the cost of these sensors is decreasing, integrating them into electric cars will increase the price and represent another barrier to adoption. The V-Charge Project, funded by the European Commission, seeks to address these problems simultaneously by developing an electric automated car, outfitted with close-to-market sen-sors, which is able to automate valet parking and recharging for integration into a future transportation system. The final goal is the demonstration of a fully operational system including automated navigation and parking. This paper presents an overview of the V-Charge system, from the platform setup to the mapping, perception, and planning sub-systems.
DIFFERENTIALLY CONSTRAINED MOTION PLANNING WITH STATE LATTICE MOTION PRIMITIVES
, 2012
"... Robot motion planning with differential constraints has received a great deal of attention in the last few decades, yet it still remains a challenging problem. Among a number of reasons, three stand out. First, the differential constraints that most physical robots exhibit render the coupling betwee ..."
Abstract
-
Cited by 5 (0 self)
- Add to MetaCart
Robot motion planning with differential constraints has received a great deal of attention in the last few decades, yet it still remains a challenging problem. Among a number of reasons, three stand out. First, the differential constraints that most physical robots exhibit render the coupling between the control and state spaces quite complicated. Second, it is commonly accepted that robots must be able to operate in environments that are partially or entirely unknown; classical motion planning techniques that assume known structure of the world frequently encounter difficulties when applied in this setting. Third, such robots are typically expected to operate with speed that is commensurate with that of humans. This poses stringent limitations on available runtime and often hard real-time requirements on the motion planner. The impressive advances in computing capacity in recent years have been unable, by themselves, to meet the computational challenge of this problem. New algorithmic approaches to tackle its difficulties continue to be developed to this day. The approach advocated in this thesis is based on encapsulating some of the complexity of satisfying the differential constraints in pre-computed controls that serve as motion primitives, elementary motions that are combined to form the solution trajectory for the system. The contribution of this work is in developing a general approach to constructing such motion primitives,
Trajectory planning with look-ahead for unmanned sea surface vehicles to handle environmental disturbances
- in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’11
, 2011
"... Abstract — We present a look-ahead based trajectory planning algorithm for computation of dynamically feasible trajectories for Unmanned Sea Surface Vehicles (USSV) operating in high seas states. The algorithm combines A * based heuristic search and locally bounded optimal planning under motion unce ..."
Abstract
-
Cited by 5 (3 self)
- Add to MetaCart
(Show Context)
Abstract — We present a look-ahead based trajectory planning algorithm for computation of dynamically feasible trajectories for Unmanned Sea Surface Vehicles (USSV) operating in high seas states. The algorithm combines A * based heuristic search and locally bounded optimal planning under motion uncertainty using a variation of the minimax game-tree search. This allows the algorithm to compute trajectories that explicitly consider the possibility of the vehicle safely deviating from its original course due to the ocean waves within a specified lookahead region. The algorithm can adapt its search based on the user-specified risk thresholds. Moreover, the algorithm produces a contingency plan as a part of the computed trajectory. We demonstrate the capabilities of the algorithm using simulations.
On the design of deformable input-/state-lattice graphs
- In Proceedings of ICRA
, 2010
"... Abstract — In this paper we describe a novel and simple to implement yet effective lattice design algorithm, which simultaneously produces input and state-space sampled lattice graphs. The presented method is an extension to the ideas suggested by Bicchi et al. on input lattices and is applicable to ..."
Abstract
-
Cited by 5 (0 self)
- Add to MetaCart
Abstract — In this paper we describe a novel and simple to implement yet effective lattice design algorithm, which simultaneously produces input and state-space sampled lattice graphs. The presented method is an extension to the ideas suggested by Bicchi et al. on input lattices and is applicable to systems which can be brought into (2,n) chained form, such as kinematic models of unicycles, bicycles, differential-drive robots and car-like vehicles (pulling several trailers). We further show that a transformation from chained form to path coordinates allows the resulting lattice to be bent along any C 1 continuous path. We exploit this fact by shaping it along the skeleton of arbitrary structured environments, such as the center of road lanes and corridors. In our experiments in both structured (i.e. on-road) and unstructured (i.e. parking lot) scenarios, we successfully demonstrate for the first time the applicability of lattice-based planning approaches to search queries in arbitrary environments. Index Terms — Non-holonomic motion planning, deformable input- / state-lattice
R.: 3D path planning and execution for search and rescue ground robots
- In: Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference on. IEEE (2013
"... Abstract — One milestone for autonomous mobile robotics is to endow robots with the capability to compute the plans and motor commands necessary to reach a defined goal position. For indoor or car-like robots moving on flat terrain, this problem is well mastered and open-source software can be deplo ..."
Abstract
-
Cited by 4 (1 self)
- Add to MetaCart
(Show Context)
Abstract — One milestone for autonomous mobile robotics is to endow robots with the capability to compute the plans and motor commands necessary to reach a defined goal position. For indoor or car-like robots moving on flat terrain, this problem is well mastered and open-source software can be deployed to such robots. However, for many applications such as search and rescue, ground robots must handle three-dimensional terrain. In this article, we present a system that is able to plan and execute a path in a complex environment starting from noisy sensor input. In order to cope with the complexity of a high-dimensional configuration space, we separate position and configuration planning. We demonstrate our system on a search and rescue robot with flippers by climbing up and down a difficult curved staircase. I.
On the Application of the D* Search Algorithm to Time-Based Planning on Lattice Graphs
, 2009
"... In this paper we present a multi-resolution state lattice, which operates in four dimensions, namely 2D position, heading, and velocity. The generation of such a lattice is described, resulting in an efficient (in terms of branching factor) and feasible (i.e. directly executable) set of edges, whic ..."
Abstract
-
Cited by 3 (1 self)
- Add to MetaCart
In this paper we present a multi-resolution state lattice, which operates in four dimensions, namely 2D position, heading, and velocity. The generation of such a lattice is described, resulting in an efficient (in terms of branching factor) and feasible (i.e. directly executable) set of edges, which can be searched on using any standard graph based planner. Furthermore, we introduce a novel heuristic, the time-viable heuristic with horizon Tn, which exploits the limited (but nonetheless extremely large) number of feasible motion combinations in a state lattice of bounded time and stores them in a look-up table. This heuristic then enables recently developed incremental planning algorithms, which typically start node expansion at the goal state (such as the various D * variants [1]) to be employed in time-based search, where the time of arrival is generally unknown a priori. We show, that by employing this technique, on average a comparable number of expanded states are to be expected for a given initial planning problem as when using forward searching algorithms (such as A * and variants [2, 3]), thus speeding up re-planning by up to two orders of magnitude as reported in [4].
Parallel Algorithms for Real-time Motion Planning
, 2011
"... For decades, humans have dreamed of making cars that could drive themselves, so that travel would be less taxing, and the roads safer for everyone. Toward this goal, we have made strides in motion planning algorithms for autonomous cars, using a powerful new computing tool, the parallel graphics pro ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
For decades, humans have dreamed of making cars that could drive themselves, so that travel would be less taxing, and the roads safer for everyone. Toward this goal, we have made strides in motion planning algorithms for autonomous cars, using a powerful new computing tool, the parallel graphics processing unit (GPU). We propose a novel five-dimensional search space formulation that includes both spatial and temporal dimensions, and respects the kinematic and dynamic constraints on a typical automobile. With this formulation, the search space grows linearly with the length of the path, compared to the exponential growth of other methods. We also propose a parallel search algorithm, using the GPU to tackle the curse of dimensionality directly and increase the number of plans that can be evaluated by an order of magnitude compared to a CPU implementation. With this larger capacity, we can evaluate a dense sampling of plans combining lateral swerves and accelerations that represent a range of effective responses to more on-road driving scenarios than have previously been addressed in the literature. We contribute a cost function that evaluates many aspects of each candidate
A.: Anytime Motion Replanning in State lattices for Wheeled Robots
- In: Workshop on Physical Agents (WAF
, 2012
"... Abstract—Autonomous robots require robust and fast motion planning algorithms to operate in complex real environments. In the last years, motion planning in state lattices has emerged as a powerful paradigm to real time path planning taking into account the kinematic restrictions of the vehicle. The ..."
Abstract
-
Cited by 3 (3 self)
- Add to MetaCart
(Show Context)
Abstract—Autonomous robots require robust and fast motion planning algorithms to operate in complex real environments. In the last years, motion planning in state lattices has emerged as a powerful paradigm to real time path planning taking into account the kinematic restrictions of the vehicle. The approach requires the definition of the state lattice and the off-line calculation of the motion primitives. Therefore, motion planning is transformed into a search problem over a directed graph. In this paper, we apply the state lattice approach for motion planning of wheeled robots usign the AD * algorithm. Thus, the planning algorithm is anytime and dynamic, i.e., the path is improved incrementally and, also, the algorithm can replan. Results of different tests on a Pioneer P3-DX show the validity of the proposal. Index Terms—motion planning, state lattices, motion primi-tives, replanning, wheeled robots. I.
