Motor skill learning by increasing the movement planning horizon
We investigated motor skill learning using a path tracking task, where human subjects had to track various curved paths as fast as possible, in the absence of any external perturbations. Subjects became better with practice, producing faster and smoother movements even when tracking novel untrained paths. Using a "searchlight" paradigm, where only a short segment of the path ahead of the cursor was shown, we found that subjects with a higher tracking skill took a longer chunk of the future path into account when computing the control policy for the upcoming movement segment. We observed the same effects in a second experiment where tracking speed was fixed and subjects were practicing to increase their accuracy. These findings demonstrate that human subjects increase their planning horizon when acquiring a motor skill.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Bootstrapping Motor Skill Learning with Motion Planning
Learning a robot motor skill from scratch is impractically slow; so much so that in practice, learning must be bootstrapped using a good skill policy obtained from human demonstration. However, relying on human demonstra…
Motion PlanningNonlinear methods to quantify Movement Variability in Human-Humanoid Interaction Activities
Human movement variability arises from the process of mastering redundant (bio)mechanical degrees of freedom to successfully accomplish any given motor task where flexibility and stability of many possible joint combinat…
DiagnosticTime SeriesTime Series AnalysisSkill-based Model-based Reinforcement Learning
Model-based reinforcement learning (RL) is a sample-efficient way of learning complex behaviors by leveraging a learned single-step dynamics model to plan actions in imagination. However, planning every action for long-h…
modelModel-based Reinforcement Learningreinforcement-learningReinforcement Learning+1Decompose and Reorganize: Planning with Primitives and Visuomotor Policies Learned from Demonstrations
Successfully automating dexterous, long-horizon robotic manipulation requires frameworks capable of both high-level reasoning and fine-grained execution. Traditional task and motion planning (TAMP), while excellent at sy…
Motion PlanningLearning robot motor skills with mixed reality
Mixed Reality (MR) has recently shown great success as an intuitive interface for enabling end-users to teach robots. Related works have used MR interfaces to communicate robot intents and beliefs to a co-located human, …
Mixed RealityWorld Knowledge