Physics-based motion planning is a challenging task, since it requires the computation of the robot motions while allowing possible interactions with (some of) the obstacles in the environment. Kinodynamic motion planners equipped with a dynamic engine acting as state propagator are usually used for that purpose. The difficulties arise in the setting of the adequate forces for the interactions and because these interactions may change the pose of the manipulatable obstacles, thus either facilitating or preventing the finding of a solution path. The use of knowledge can alleviate the stated difficulties. This paper proposes the use of an enhanced state propagator composed of a dynamic engine and a low-level geometric reasoning process that is used to determine how to interact with the objects, i.e. from where and with which forces. The proposal, called ¿-PMP can be used with any kinodynamic planner, thus giving rise to e.g. ¿-RRT. The approach also includes a preprocessing step that infers from a semantic abstract knowledge described in terms of an ontology the manipulation knowledge required by the reasoning process. The proposed approach has been validated with several examples involving an holonomic mobile robot, a robot with differential constraints and a serial manipulator, and benchmarked using several state-of-the art kinodynamic planners. The results showed a significant difference in the power consumption with respect to simple physics-based planning, an improvement in the success rate and in the quality of the solution paths.
Programming by demonstration techniques facilitate the programming of robots. Some of them allow the generalization of tasks through parameters, although they require new training when trajectories different from the ones used to estimate the model need to be added. One of the ways to re-train a robot is by incremental learning, which supplies additional information of the task and does not require teaching the whole task again. The present study proposes three techniques to add trajectories to a previously estimated task-parameterized Gaussian mixture model. The first technique estimates a new model by accumulating the new trajectory and the set of trajectories generated using the previous model. The second technique permits adding to the parameters of the existent model those obtained for the new trajectories. The third one updates the model parameters by running a modified version of the Expectation-Maximization algorithm, with the information of the new trajectories. The techniques were evaluated in a simulated task and a real one, and they showed better performance than that of the existent model.
The final publication is available at link.springer.com
Santamaria, E.; Pastor, E.; Barrado, C.; Prats, X.; Royo, P.; Perez-Batlle, M. Journal of intelligent and robotic systems Vol. 67, num. 2, p. 155-181 DOI: 10.1007/s10846-011-9648-3 Data de publicació: 2012-07 Article en revista
This paper presents a new concept for specifying Unmanned Aircraft Systems (UAS) flight operations that aims at improving the waypoint based approach, found in most autopilot systems, by providing higher level fligh plan specification primitives. The proposed method borrows the leg and path terminator concepts used in Area Navigation1 (RNAV). Several RNAV leg types are adopted and extended with new ones for a better adaptation to UAS requirements. Extensions include the addition of control constructs that enable repetitive and conditional behavior, and also parametric legs that can be used to generate complex paths from a reduced number of parameters. The paper also covers the design and implementation of a software component that manages execution of the flight plan. To take advantage of current off-the-shelf flight control systems the constructs included in the flight plan are translated to waypoint navigation commands. In this way, the advanced capabilities provided by the flight plan specification language are implemented as a new layer on top of existing technologies. The benefits and the feasibility of the proposed approach for UAS flight plan management are demonstrated by means of a simulated mission that performs the flight inspection of Radio Navigation Aids.
Ramisa, A.; Aldavert , D.; Vasudeban, S.; Toledo, R.; López, R. Journal of intelligent and robotic systems Vol. 68, num. 2, p. 185-208 DOI: 10.1007/s10846-012-9675-8 Data de publicació: 2012 Article en revista
This paper addresses visual object perception applied to mobile robotics. Being able to perceive household objects in unstructured environments is a key capability in order to make robots suitable to perform complex tasks in home environments. However, finding a solution for this task is daunting: it requires the ability to handle the variability in image formation in a moving camera with tight time constraints. The paper brings to attention
some of the issues with applying three state of the art object recognition and detection methods in a mobile robotics scenario, and proposes methods to deal with windowing/segmentation. Thus, this work aims at evaluating the state-of-the-art in object perception in an attempt to develop a lightweight solution for mobile robotics use/research in typical indoor settings.
Ramisa, A.; Goldhoorn, A.; Aldavert, D.; Toledo, R.; López, R. Journal of intelligent and robotic systems Vol. 64, num. 3-4, p. 625-649 DOI: 10.1007/s10846-011-9552-x Data de publicació: 2011-12-01 Article en revista
Biologically inspired homing methods, such as the Average Landmark Vector, are an interesting solution for local navigation due to its simplicity. However, usually they require a modification of the environment by placing artificial landmarks in order to work reliably. In this paper we combine the Average Landmark Vector with invariant feature points automatically detected in panoramic images to overcome this limitation. The proposed approach has been evaluated first in simulation and, as promising results are found, also in two data sets of panoramas from real world environments.