In this work, an explicitly task-oriented approach to the active vision problem is presented. The system tries to reduce the most relevant components of the uncertainty in the world model, for the task the robot is currently performing. It is task oriented in the sense that it explicitly considers a task-specific value function. As test-bed for the presented active vision approach, we selected a robot soccer attention problem: goal-covering by a goalie player. The proposed system is compared with information-based approaches. Experimental results show that it surpasses them in the tested application. We conclude that, when the goal is not the uncertainty reduction itself, the minimization of the belief entropy is not a useful optimality criterion, and that for such cases, task-oriented optimality criteria are better suited.

No abstract

No abstract

A Carrier Ethernet Network (CEN) is a versatile, standardized, ubiquitous, carrier-class network. It possess several attributes that distinguish it from Metro Ethernet Networks (MENs), quality of service (QoS) being an integral one. Because CENs are designed to cover large areas (thousands of km) and transmit at high data rates (100 Gbps), these networks have a high bandwidth-delay product (BDP). Long distance transmissions that require data integrity suffer a transport-layer throughput bottleneck effect. Under these conditions, systems (including testbeds) exhibit a detrimental performance evaluation reduction as the round-trip time (RTT) increases. A new transport protocol is proposed to overcome the difficulties these networks incur, while providing QoS guarantees at the transport-layer level, hence maintaining the committed throughput levels established in the service level agreement (SLA). The proposed protocol, which is called Ethernet Services transport protocol (ESTP), is able to obtain congestion level feedback using only layer-4 information rather than assuming congestion based on a single packet loss event. An important aspect of this work is that it is validated by theoretical, simulated, and experimental results.