Key to determining what is and is not important is understanding the metric by which the robot's behavior is being evaluated. For a given task, certain observable or affectable properties of the environment may be irrelevant and safely ignored. What to imitate relates to the problem of determining which aspects of the demonstration should be imitated.
#Robocop 2003 demo how to#
Nehaniv & Dautenhahn (2001) phrased the problems faced by LfD - PbD in a set of key questions: '’'What to imitate? How to imitate? When to imitate? Whom to imitate?'’' To date, only the first two questions have really been addressed in LfD - PbD. Key Issues in Programming by Demonstration / Learning from Demonstration 2006, Dautenhahn and Nehaniv 2002, Billard 2002, Breazeal and Scassellati 2002). Surveys in this area can be found in (Oztop et al. Others pursue a more cognitive science approach and build conceptual model of imitation learning in animals. Some of these works pursue a computational neuroscience approach and use neural modeling. A large body of work on LfD - PbD therefore takes inspiration from concepts in psychology and biology. Surveys of works in this area include (Argall et al 2010 Billard et al 2013, Schaal et al 2003).Īt the core, however, LfD - PbD is inspired by the way humans learn from being guided by experts, from infancy through adulthood. The vast majority of work on LfD - PbD follows a more engineering/machine learning approach. Research on LfD - PbD has grown steadily in importance since the 80s and several surveys have been published in recent years. Furthermore, by utilizing expert knowledge from the user, in the form of demonstrations, the actual learning should be fast compared to current trial-and-error learning, particularly in high dimensional spaces (henceforth addressing part of the well-known curse of dimensionality). The expectation is that the methods of LfD-PbD, being user-friendly, will allow robots to be utilized to a greater extent in day-to-day interactions with non-specialist humans. LfD - PbD seeks to minimize, or even eliminate, this difficult step by letting users train their robot to fit their needs. Then, and still to a large extent now, robots had to be tediously hand programmed for every task they performed. Robot Learning from Demonstration started in the 1980s. Learning and generalizing is core to LfD - PbD.įigure 2: After learning, the robot successfully reproduces the task even when all objects are in novel positions. LfD - PbD is NOT a record and replay technique. LfD - PbD hence seeks to endow robots with the ability to learn what it means to perform a task by generalizing from observing several demonstrations, see Figure 1.
#Robocop 2003 demo professional#
Then, when failures occur, the end-user needs only to provide more demonstrations, rather than calling for professional help. In contrast, LfD - PbD allows the end-user to 'program' the robot simply by showing it how to perform the task - no coding required. If errors or new circumstances arise after the robot is deployed, the entire costly process may need to be repeated, and the robot recalled or taken out of service while it is fixed. This process may involve breaking down the task into 100s of different steps, and thoroughly testing each step.
#Robocop 2003 demo code#
In a traditional programming scenario, a human programmer would have to reason in advance and code a robot controller that is capable of responding to any situation the robot may face, no matter how unlikely. Furthermore, each time this task is performed, the robot will need to contend with changes such as displacement of the items' locations. The task itself may involve multiple subtasks, such as juicing the orange, throwing the rest of the orange in the trash and pouring the liquid in a cup. Consider, for example, a domestic service robot that an owner wishes to have prepare orange juice for breakfast, see Figure 1. The main principle of robot LfD-PbD is that end-users can teach robots new tasks without programming. 4.2 LfD - PbD and Human-Robot Interaction.4.1 Imitation Learning and Reinforcement Learning.4 Imitation Learning combined with Other Learning Techniques.3.2 Learning high-level action composition.3.1 Low level learning of individual motions.2.2 How to Imitate and the Notion of Correspondence.2.1 What to imitate and Evaluation Metric.2 Key Issues in Programming by Demonstration / Learning from Demonstration.