The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In our previous work [1] we introduced the Anticipative Kinodynamic Planning (AKP): a robot navigation algorithm in dynamic urban environments that seeks to minimize its disruption to nearby pedestrians. In the present paper, we maintain all the advantages of the AKP, and we overcome the previous limitations by presenting novel contributions to our approach. Firstly, we present a multi-objective cost...
This paper presents a novel approach to modeling the dynamics of human movements with a grid-based representation. The model we propose, termed as Multi-scale Conditional Transition Map (MCTMap), is an inhomogeneous HMM process that describes transitions of human location state in spatial and temporal space. Unlike existing work, our method is able to capture both local correlations and long-term...
This paper proposes a methodology for visual tracking of a dynamic generalized subject within an unknown map, by relying on its perception as a separate entity which can be distinguished spatially and visually from its environment. To this purpose, a 3D-representation of the visible scenery is examined, and the subject is spatially identified by its externally viewed hull via a mesh-connection algorithm...
The identification of the dynamic model of a robotic manipulator represents a fundamental step for designing high performance model-based controllers. Despite the huge number of works presented on this topic, the symbolic dynamic model reduction (i.e., the identification of the set of parameters observable through the measure of joint torques and positions) still remain a challenging task, characterized...
We consider discriminative dictionary learning in a distributed online setting, where a team of networked robots aims to jointly learn both a common basis of the feature space and a classifier over this basis from sequentially observed signals. We formulate this problem as a distributed stochastic program with a non-convex objective and present a block variant of the Arrow-Hurwicz saddle point algorithm...
Applications of reinforcement learning for robotic manipulation often assume an episodic setting. However, controllers trained with reinforcement learning are often situated in the context of a more complex compound task, where multiple controllers might be invoked in sequence to accomplish a higher-level goal. Furthermore, training such controllers typically requires resetting the environment between...
In this paper we derive and implement an algorithm for an indoor mobile robotics platform to estimate the manipulability of initially unknown obstacles while navigating through its environment to a pre-specified goal. The environment is represented by an evidence grid, where each cell contains a gamma-distributed cost as well as visual feature data in the form of a color histogram. While navigating,...
In order to fully exploit the capabilities of a robotic systems, it is necessary to consider the limitations and errors of actuators and sensors already during the motion planning phase. In this paper, a framework for path planning is introduced, that uses heuristic search to build up a search graph in belief space, an extension to the deterministic state space considering the uncertainty associated...
This paper deals with motion planning problems for spherical rolling robots driven by a two degree of freedom pendulum. A full dynamic model for this system is first introduced. Then, assuming that the contact path is specified and the sphere moves in pure rolling mode, the full dynamic model is reduced by imposing virtual constraints. A timing control law, based on the Beta function, for tracing...
We consider the problem of computing the inverse dynamics of a serial robot manipulator with N elastic joints in a recursive numerical way. The solution algorithm is a generalized version of the standard Newton-Euler approach, running still with linear complexity O(N) but requiring to set up recursions that involve higher order derivatives of motion and force variables. Mimicking the case of rigid...
Cyber-physical systems (CPS) combine cyber aspects such as communication and computer control with physical aspects such as movement in space, which arise frequently in many safety-critical application domains, including aviation, automotive, railway, and robotics. But how can we ensure that these systems are guaranteed to meet their design goals, e.g., that an aircraft will not crash into another...
This paper presents a recursive and parallel formulation for the dynamics simulation of large articulated robotic systems based on the Hamilton's canonical equations. Although Hamilton's canonical equations exhibit many advantageous features compared to their acceleration based counterparts, it appears that there is a lack of dedicated parallel algorithms for multi-rigid body dynamics simulation based...
This paper proposes a Rapidly exploring Random Trees planning strategy (Poli-RRT*) that computes optimal trajectories in presence of vehicle constraints (e.g., differential and actuation constraints) without approximating the nonlinear dynamics, but relying on exact linearisation. In this way, the optimal control problem that is introduced to determine the trajectories extending the tree can be expressed...
In this paper, we develop an receding horizon control (RHC) law for controlling the pursuers in a pursuit-evasion problem arising in a harbor defense scenario and describe its real-time implementation that we apply experimentally to a robotic testbed. Our implementation of the RHC law makes use of a min-max formulation of the underlying optimal problem that must be solved at each sample time, which...
This paper addresses distributed average tracking for a group of physical double-integrator agents under an undirected graph without using velocity measurements. We introduce a discontinuous algorithm and filter to allow the agents to track the average of time-varying signals, where each agent needs the relative positions between itself and its neighbors and its neighbors' filter outputs but the requirement...
It is challenging to realize robotic catching of small fast-moving targets in a large workspace, especially for targets with random trajectories that are difficult to predict. It requires high-speed and accurate motion control, whereas these two aspects usually conflict with each other due to the robot's nonlinear dynamics and systematic uncertainties like backlash. Previously, we proposed a dynamic...
In many Multi Agent Systems, under-education agents investigate their environments to discover their target(s). Any agent can also learn its strategy. In multitask learning, one agent studies a set of related problems together simultaneously, by a common model. In reinforcement learning exploration phase, it is necessary to introduce a process of trial and error to learn better rewards obtained from...
This paper presents an extension of our previous work on hybrid metric/topological maps to enable uncertainty reduction planning through the map, taking into account both map uncertainty and distance. An enhancement of the edge structure which enables the simulation of bidirectional edge propagation through an extended Kalman filter is proposed in our heuristic search planning algorithm to plan for...
Motion planning under differential constraints is a classic problem in robotics. To date, the state of the art is represented by sampling-based techniques, with the Rapidly-exploring Random Tree algorithm as a leading example. Yet, the problem is still open in many aspects, including guarantees on the quality of the obtained solution. In this paper we provide a thorough theoretical framework to assess...
Several sampling-based algorithms have been recently proposed that ensure asymptotic optimality. The convergence of these algorithms can be improved if sampling is guided toward the most promising region of the search space where the solution is more likely to be found. In this paper we propose three sample rejection methods that leverage the classification of the samples according to their potential...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.