Recent works present deep reinforcement learning as a framework to model the complex interactions and cooperation. This work extends our previous approach to develop an algorithm that learns collision avoidance among a variety of types of dynamic agents without assuming they follow any particular behavior rules.
In this paper, we present a neural network-based adaptive sampler for motion planning called Deep Sampling-based Motion Planner (DeepSMP). DeepSMP's neural architecture comprises of a Contractive AutoEncoder which encodes given workspaces directly from a raw point cloud data, and a Dropout-based stochastic deep feedforward neural network which takes the workspace encoding, start and goal configuration, and iteratively generates feasible samples for SMPs to compute end-to-end collision-free optimal paths.
Fast and efficient motion planning algorithms are crucial for many state-of-the-art robotics applications such as self-driving cars. Existing motion planning methods such as RRT*, A*, and D*, become ineffective as their computational complexity increases exponentially with the dimensionality of the motion planning problem.
Many planning applications involve complex relationships defined on high-dimensional, continuous variables. For example, robotic manipulation requires planning with kinematic, collision, and motion constraints involving robot configurations, object transforms, and robot trajectories.
Many robotic planning applications involve continuous actions with highly non-linear constraints, which cannot be modeled using modern planners that construct a propositional representation. We introduce STRIPStream: an extension of the STRIPS language which can model these domains by supporting the specification of blackbox generators to handle complex constraints.
Bayesian optimization usually assumes that a Bayesian prior is given. However, the strong theoretical guarantees in Bayesian optimization are often regrettably compromised in practice because of unknown parameters in the prior.
Our aim is to reduce the expected number of collision checks by creating a belief model of the configuration space using results from collision tests. We have also proposed a weighting matrix in C-space to improve the performance of kNN methods.
We propose a learning method that we call CAD$^2$RL, which can be used to perform collision-free indoor flight in the real world while being trained entirely on 3D CAD models. This policy is trained entirely on simulated images, with a Monte Carlo policy evaluation algorithm that directly optimizes the network's ability to produce collision-free flight.