The article presents the experimental evaluation of an integrated approach for path following and obstacle avoidance, implemented on wheeled robots. Wheeled robots are widely used in many different contexts, and they are usually required to operate in partial or total autonomy: in a wide range of situations, having the capability to follow a predetermined path and avoiding unexpected obstacles is extremely relevant. The basic requirement for an appropriate collision avoidance strategy is to sense or detect obstacles and make proper decisions when the obstacles are nearby. According to this rationale, the approach is based on the definition of the path to be followed as a curve on the plane expressed in its implicit form f(x, y) = 0, which is fed to a feedback controller for path following. Obstacles are modeled through Gaussian functions that modify the original function, generating a resulting safe path which – once again – is a curve on the plane expressed as f′(x, y) = 0: the deformed path can be fed to the same feedback controller, thus guaranteeing convergence to the path while avoiding all obstacles. The features and performance of the proposed algorithm are confirmed by experiments in a crowded area with multiple unicycle-like robots and moving persons.

Latency hinders a mobile robot teleoperator's ability to perform remote tasks. However, this effect is not well modeled. This paper develops a model for teleoperator steering behavior as a PD controller based on projected lateral displacement, which was tuned to reflect user performance determined by a 31-subject user study under constant and variable latency (having mean latencies between 0 and 750 ms). Additionally, we determined that operator performance under variable latency could be mapped to the expected performance of an equivalent constant latency. We then tested additional latency distributions in simulation and demonstrated equivalent steering performance among several different latency distributions.

This paper introduces a novel approach to motion planning for a rapid mobile manipulator using inverted pendulum models. Our aim was to realize an actual rapid mobile manipulator with high acceleration and speed performance for an object's delivery. In our research, we developed an actual rapid mobile manipulator called KDMR-1. We proposed simple motion planning methods using a single inverted pendulum model (SIPM) and a double inverted pendulum model (DIPM), which are easily adaptable to a real-time system with only a small computational burden. The SIPM was useful for basic movement but did not provide object carrying capability. For that, a DIPM was proposed. In both models, we designed linear quadratic optimal controllers to stabilize the Zero Moment Point (ZMP). Two kinds of ZMP stabilization strategies were proposed, fixed ZMP and relaxed ZMP. Using these strategies, we realized optimal ZMP stabilizations for a real-time rapid mobile manipulator. For decoupled forward and rotational linear DIPM, we designed a centrifugal acceleration compensation model in the manner of feedback linearization. The experimental results showed high acceleration and speed performances during rapid object delivery.

This paper presents a motion planning method for a simple wheeled robot in two cases: (i) where translational and rotational speeds are arbitrary, and (ii) where the robot is constrained to move forwards at unit speed. The motions are generated by formulating a constrained optimal control problem on the Special Euclidean group SE(2). An application of Pontryagin's maximum principle for arbitrary speeds yields an optimal Hamiltonian which is completely integrable in terms of Jacobi elliptic functions. In the unit speed case, the rotational velocity is described in terms of elliptic integrals, and the expression for the position is reduced to quadratures. Reachable sets are defined in the arbitrary speed case, and a numerical plot of the time-limited reachable sets is presented for the unit speed case. The resulting analytical functions for the position and orientation of the robot can be parametrically optimised to match prescribed target states within the reachable sets. The method is shown to be easily adapted to obstacle avoidance for static obstacles in a known environment.