相关论文: Literal or Pedagogic Human? Analyzing Human Model …
While reinforcement learning provides an appealing formalism for learning individual skills, a general-purpose robotic system must be able to master an extensive repertoire of behaviors. Instead of learning a large collection of skills…
The visual world is very rich and generally too complex to perceive in its entirety. Yet only certain features are typically required to adequately perform some task in a given situation. Rather than hardwire-in decisions about when and…
Robot understanding of human intentions is essential for fluid human-robot interaction. Intentions, however, cannot be directly observed and must be inferred from behaviors. We learn a model of adaptive human behavior conditioned on the…
Successful teaching entails a complex interaction between a teacher and a learner. The teacher must select and convey information based on what they think the learner perceives and believes. Teaching always involves misaligned beliefs, but…
Assuming humans are (approximately) rational enables robots to infer reward functions by observing human behavior. But people exhibit a wide array of irrationalities, and our goal with this work is to better understand the effect they can…
As robot deployments become more commonplace, people are likely to take on the role of supervising robots (i.e., correcting their mistakes) rather than directly teaching them. Prior works on Learning from Corrections (LfC) have relied on…
Robots that interact with humans in a physical space or application need to think about the person's posture, which typically comes from visual sensors like cameras and infra-red. Artificial intelligence and machine learning algorithms use…
Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains…
The development of the works of the author about adaptive algorithms of teaching the robotic systems with the help of operator is described here. An operator is assumed to be an experience decision-maker and sane carrier of a target which…
Autonomous robots must communicate about their decisions to gain trust and acceptance. When doing so, robots must determine which actions are causal, i.e., which directly give rise to the desired outcome, so that these actions can be…
A common assumption in machine learning is that training data are i.i.d. samples from some distribution. Processes that generate i.i.d. samples are, in a sense, uninformative---they produce data without regard to how good this data is for…
The object of the research is the adaptive algorithms that are used by the operator when educating the robotic systems. Operator, being the target-setting subject, is interested in the goal that robotic systems, being the conductor of his…
As human machine teaming becomes central to paradigms like Industry 5.0, a critical need arises for machines to safely and effectively interpret complex human behaviors. A research gap currently exists between techno centric robotic…
Robots can learn the right reward function by querying a human expert. Existing approaches attempt to choose questions where the robot is most uncertain about the human's response; however, they do not consider how easy it will be for the…
Humans can leverage physical interaction to teach robot arms. This physical interaction takes multiple forms depending on the task, the user, and what the robot has learned so far. State-of-the-art approaches focus on learning from a single…
When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format…
The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming, in which the designer-provided specification is flawed in a…
A longstanding goal of artificial intelligence is to create artificial agents capable of learning to perform tasks that require sequential decision making. Importantly, while it is the artificial agent that learns and acts, it is still up…
Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of…
Human-in-the-loop learning is gaining popularity, particularly in the field of robotics, because it leverages human knowledge about real-world tasks to facilitate agent learning. When people instruct robots, they naturally adapt their…