E.J. Perez

A New Efficiency-Weighted Strategy for Continuous Human/Robot Cooperation in Navigation

Autonomous robots are capable of navigating on their own. Shared control approaches, however, allow humans to make some navigation decisions. This is typically executed either by overriding the human or the robot control at some specific situations. In this paper, we propose a method to allow cooperation between humans and robots at each point of any given trajectory so that both have some weight in the emergent behavior of the mobile robot. This is achieved by evaluating their efficiencies at each time instant and combining their commands into a single order. In order to achieve a seamless combination, this procedure is integrated into a bottom-up architecture via a reactive layer. We have tested the proposed method using a real robot and several volunteers, and results have been satisfactory both from a quantitative and qualitative point of view.

Hierarchical planning in a mobile robot for map learning and navigation

This chapter focuses on autonomous navigation for mobile robots. We propose a hybrid layered architecture, which is used to navigate in totally or partially explored environments using sonar sensors. Our architecture relies on a hierarchical representation of the environment, which has both a metric and a topological level, which is based on the metric level. High level planning layers work at the topological level deliberatively, while low level navigation layers operate at the metric level reactively. The main advantage of the proposed scheme is that it can operate in both known and unknown environments rapidly and efficiently.

Efficient integration of metric and topological maps for directed exploration of unknown environments

Recent research in mobile robot navigation is focused on integrating the metric and topological paradigms to unsupervisedly construct representations of indoor environments. While metric methods produce accurate environment representations, these representations present a huge data volume and they are consequently difficult to process in real time. On the other hand, topological maps can be processed in a more efficient way, but they are typically difficult to disambiguate and update. This paper describes an exploration algorithm for totally or partially unexplored environments. The algorithm is based on a representation that integrates the metric and topological paradigms. Exploration planning is performed at two levels: global planning is performed at topological level and local planning is performed at metric level. The main advantage of the proposed algorithm is that exploration can be performed in a fast and efficient way by using the presented representation. The method has been successfully tested for a Pioneer P2AT mobile robot in indoor environments.

A purely reactive navigation scheme for dynamic environments using Case-Based Reasoning

This paper presents a new sonar based purely reactive navigation technique for mobile platforms. The method relies on Case-Based Reasoning to adapt itself to any robot and environment through learning, both by observation and self experience. Thus, unlike in other reactive techniques, kinematics or dynamics do not need to be explicitly taken into account. Also, learning from different sources allows combination of their advantages into a safe and smooth path to the goal. The method has been succesfully implemented on a Pioneer robot wielding 8 Polaroid sonar sensors.

On the Construction of a Skill-Based Wheelchair Navigation Profile

Assisted wheelchair navigation is of key importance for persons with severe disabilities. The problem has been solved in different ways, usually based on the shared control paradigm. This paradigm consists of giving the user more or less control on a need basis. Naturally, these approaches require personalization: each wheelchair user has different skills and needs and it is hard to know a priori from diagnosis how much assistance must be provided. Furthermore, since there is no such thing as an average user, sometimes it is difficult to quantify the benefits of these systems. This paper proposes a new method to extract a prototype user profile using real traces based on more than 70 volunteers presenting different physical and cognitive skills. These traces are clustered to determine the average behavior that can be expected from a wheelchair user in order to cope with significant situations. Processed traces provide a prototype user model for comparison purposes, plus a simple method to obtain without supervision a skill-based navigation profile for any user while he/she is driving. This profile is useful for benchmarking but also to determine the situations in which a given user might require more assistance after evaluating how well he/she compares to the benchmark. Profile-based shared control has been successfully tested by 18 volunteers affected by left or right brain stroke at Fondazione Santa Lucia, in Rome, Italy.

A Hough-based method for concurrent mapping and localization in indoor environments

This paper proposes a method to solve the simultaneous localization and map building problem based on segments extracted from local sonar based occupation maps. These segments are categorized as new obstacle boundaries of a simultaneously built global segment-based map or as prolongations of previously extracted boundaries. The method is adequate for indoor office-like environments, specially for those environments that can be suitable modelled by a set of segments. The method has been proved in several experiments in the same indoor environment with successful results.

A hybrid architecture for autonomous navigation using a CBR reactive layer

This paper presents a hybrid architecture for autonomous robot navigation. It includes a deliberative layer that hierarchically extracts a global path from a geometrical-topological model of the environment. This path is decomposed into a set of partial goals. Then, a new case-based reasoning based reactive layer capable of learning new local navigation strategies moves from each partial goal to the next. The architecture has been successfully tested in real dynamic environments.

A HYBRID PATH PLANNING TECHNIQUE FOR PARTIALLY UNKNOWN INDOOR ENVIRONMENTS

This paper presents an exploration algorithm for partially or totally unknown environrnents. The method is based on a representation that integrates metric and topological pazadigms. The metric paradigm produces an accurate representation of the environrent. The topological map is built over the metric map by means of a hierarchical structure. It reduces the metric data volume and can be processed in a more efficient way. The representation of the environrent is used to calculate a route through unexplored areas. The main advantage of the proposed scheme is that it can operate in known and urdmown areas in a fast and efficient way.

A time stamp control strategy for CBR based reactive navigation in dynamic environments with priorities

This work presents a CBR based reactive navigation system for autonomous robots. The main advantage of the proposed system is that it learns by experience how to deal with unexpected situations in dynamic environments. A time stamp control method has been included to deal with mobile obstacles in intersections, where there are priorities depending on the relative positions of those obstacles and the robot. The proposed strategy has been successfully tested in real environments.