References of "Ertle, P"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailConceptual Design of a Dynamic Risk-Assessment Server for Autonomous Robots
Ertle, P.; Tokic, M.; Bystricky, T. et al

in 7th German Conference on Robotics (Robotik 2012) (2012)

Future autonomous service robots are intended to operate in open and complex environments. This in turn implies complications ensuring safe operation. The tenor of few available investigations is the need ... [more ▼]

Future autonomous service robots are intended to operate in open and complex environments. This in turn implies complications ensuring safe operation. The tenor of few available investigations is the need for dynamically assessing operational risks. Furthermore, there is a new kind of hazards being implicated by the robot’s capability to manipulate the environment: Hazardous environmental object interactions. Therefore, the realization of the Dynamic Risk-Assessment approach with special scope on object-interaction risks is addressed in this paper. A server-based architecture is proposed facilitating a feasible integration into robotic systems and realization of software and hardware redundancy as well. [less ▲]

Detailed reference viewed: 36 (1 UL)
Full Text
Peer Reviewed
See detailRobust Exploration/Exploitation Trade-Offs in Safety-Critical Applications
Tokic, M.; Ertle, P.; Palm, G. et al

in 8th IFAC Int. Symposium on Fault Detection, Supervision and Safety for Technical Processes, Mexico City 29-31 August 2012 (2012)

With regard to future service robots, unsafe exceptional circumstances can occur in complex systems that are hardly to foresee. In this paper, the assumption of having no knowledge about the environment ... [more ▼]

With regard to future service robots, unsafe exceptional circumstances can occur in complex systems that are hardly to foresee. In this paper, the assumption of having no knowledge about the environment is investigated using reinforcement learning as an option for learning behavior by trial-and-error. In such a scenario, action-selection decisions are made based on future reward predictions for minimizing costs in reaching a goal. It is shown that the selection of safetycritical actions leading to highly negative costs from the environment is directly related to the exploration/exploitation dilemma in temporal-di erence learning. For this, several exploration policies are investigated with regard to worst- and best-case performance in a dynamic environment. Our results show that in contrast to established exploration policies like epsilon-Greedy and Softmax, the recently proposed VDBE-Softmax policy seems to be more appropriate for such applications due to its robustness of the exploration parameter for unexpected situations. [less ▲]

Detailed reference viewed: 44 (1 UL)
Full Text
Peer Reviewed
See detailUtilizing Dynamic Hazard Knowledge for Risk Sensitive Action Planning of Autonomous Robots
Ertle, P.; Voos, Holger UL; Soeffker, D.

in IEEE Int. Symposium on Robotics and Sensor Environments ROSE, Magdeburg, Germany, 2012 (2012)

Autonomous robots are required to perform tasks in complex and dynamic environments. For this class of systems, traditional safety assuring methods are not satisfying due to the unknown effects of the ... [more ▼]

Autonomous robots are required to perform tasks in complex and dynamic environments. For this class of systems, traditional safety assuring methods are not satisfying due to the unknown effects of the interacting system with an open environment. Briefly speaking: What is not known during the development phase can not be adequately considered. In order to tackle this problem, it is proposed to extend the safety measures with the so-called dynamic risk assessment. Therefore, the anticipatory capability of a Cognitive Technical System, the so-called mental action space, is utilized. The mental action space, a learned internal representation for possible courses of action, is dynamically assessed. The proposed dynamic risk assessment module provides this functionality. The core are quantitative risk models, so-called ‘safety principles’, which can be specified during the system’s design stage without losing the possibility to be adjusted or extended during the system’s operating time. Finally, an exemplary application of the approach shows a robot, enabled to safely plan and perform its tasks concerning risks arising due to interaction of robot and environment. [less ▲]

Detailed reference viewed: 50 (4 UL)
Full Text
Peer Reviewed
See detailTowards Learning of Safety Knowledge from Human Demonstrations
Ertle, P.; Tokic, M.; Cubek, R. et al

in IEEE/RSJ Int. Conference on Intelligent Robots and Systems IROS, Vilamoura 7-12 Oct. 2012 (2012)

Future autonomous service robots are intended to operate in open and complex environments. This in turn implies complications ensuring safe operation. The tenor of few available investigations is the need ... [more ▼]

Future autonomous service robots are intended to operate in open and complex environments. This in turn implies complications ensuring safe operation. The tenor of few available investigations is the need for dynamically assessing operational risks. Furthermore, a new kind of hazards being implicated by the robot’s capability to manipulate the environment occurs: hazardous environmental object interactions. One of the open questions in safety research is integrating safety knowledge into robotic systems, enabling these systems behaving safety-conscious in hazardous situations. In this paper a safety procedure is described, in which learning of safety knowledge from human demonstration is considered. Within the procedure, a task is demonstrated to the robot, which observes object-to-object relations and labels situational data as commanded by the human. Based on this data, several supervised learning techniques are evaluated used for finally extracting safety knowledge. Results indicate that Decision Trees allow interesting opportunities. [less ▲]

Detailed reference viewed: 38 (2 UL)