An improved Q-learning algorithm with a modified action-value function and reward-penalty scheme generates time-optimal robot trajectories that respect velocity-dependent piecewise-linear torque constraints.
Sousa, Dynamic model identification of robot manipulators: Solving the physical feasibility problem, Universidade de Coimbra, Portugal
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reinforcement Learning for Robotic Time-optimal Path Tracking Using Prior Knowledge
An improved Q-learning algorithm with a modified action-value function and reward-penalty scheme generates time-optimal robot trajectories that respect velocity-dependent piecewise-linear torque constraints.