Set Of Motion Primitives Research Articles

Radar-based path planning of autonomous surface vehicle with static and dynamic obstacles in a Frenet Frame

AbstractNavigation safety at sea is vital for each autonomous surface vehicle (ASV), which involves the problem of motion planning in dynamic environments and their robust tracking through feedback control. We present a practical path-planning method that generates smooth trajectories for a marine vehicle traveling in an unknown environment, where obstacles are detected in real time by millimetre wave (mmWave) radar. Our approach introduces a polynomial curve to describe the lateral and longitudinal trajectories in the Frenet frame, known as the ‘motion primitives’, whose combination ensures that the planning area is properly covered. In addition, we can select a feasible, optimal and collision-free trajectory from such a set of motion primitives that is generated by considering the vehicle dynamics and comfort. The capabilities of proposed algorithm are demonstrated in the experiment with static and dynamic obstacles.

Radar-based maritime path planning with static obstacles in a Frenet frame

<p indent=0mm>Navigation safety at sea is important for autonomous surface vehicles, and involves the problems of motion planning in dynamic environments and their robust tracking through feedback control. We present a practical path planning method that generates smooth trajectories for a high-speed marine vehicle traveling in an unknown environment, where obstacles are detected in real time by marine radar. Our approach uses the polynomial curve to describe lateral and longitudinal trajectories in the Frenet frame, known as motion primitives, whose combination ensures that the planning area is properly covered. In addition, we can select a feasible, optimal, and collision-free trajectory from such a set of motion primitives that is generated by considering the vehicle dynamics and comfort. The effectiveness of the proposed algorithm is demonstrated in an experiment with static and dynamic obstacles.

Efficient policy search in low-dimensional embedding spaces by generalizing motion primitives with a parameterized skill memory

Motion primitives are an established paradigm to generate complex motions from simpler building blocks. A much less addressed issue is at which level to encode and how to organize a library of motion primitives. Typically, the intrinsic variability of a skill is significantly lower-dimensional than the parameter space of motion primitive models. This paper therefore proposes a parameterized skill memory in a first step, which organizes a set of motion primitives in a low-dimensional, topology-preserving embedding space. The skill memory acts as a pivotal mechanism that links low-dimensional skill parametrization to motion primitive parameters and complete motion trajectories. The skill memory is implemented by means of a dynamical system which features continuous generalization of motion shapes and the multi-directional retrieval of motion primitive parameters from low-dimensional skill parametrizations. The skill parametrization can be predefined or automatically discovered, e.g. by unsupervised dimension reduction techniques. The paper shows that parameterized skill memories achieve excellent generalization of motion shapes from few training examples in several scenarios, including the bi-manual manipulation of a rod with the humanoid robot iCub. In a second step, the low-dimensional and topological skill parametrization is leveraged for efficient, gradient-based policy search. Policy search by generalizing motion shapes from low-dimensional parametrizations is compared to conventional policy search in the parameter space of a motion primitive model. It turns out that the reduced search space accessible through the skill memory significantly accelerates the policy improvement.

Simulating Motion Elements of General-Purpose Robot Arms

Robot arm displacement curves are constructed, assuming that all links in the arm are rigid. This can be accomplished by using familiar, cam-motion profile techniques whenever possible. The benefits of these considerations can help achieve smoother motion while minimizing wear on and effort by the robot actuators. A set of motion primitives within the General Robot Arm Simulation Program ( GRASP) are presented as examples.