Randomized trials are widely considered as the gold standard for evaluating the effects of decision policies.

Tilt-rotor aerial robots are more dynamic and versatile than their fixed-rotor counterparts, since the thrust vector and body orientation are decoupled. However, the coordination of servomotors and propellers (the allocation problem) is not trivial, especially accounting for overactuation and actuator dynamics. We present and compare different methods of actuator allocation for tilt-rotor platforms, evaluating them on a real aerial robot performing dynamic trajectories. We extend the state-of-the-art geometric allocation into a differential allocation, which uses the platform's redundancy and does not suffer from singularities typical of the geometric solution. We expand it by incorporating actuator dynamics and introducing propeller limit curves. These improve the modeling of propeller limits, automatically balancing their usage and allowing the platform to selectively activate and deactivate propellers during flight. We show that actuator dynamics and limits make the tuning of the allocation not only easier, but also allow it to track more dynamic oscillating trajectories with angular velocities up to 4 rad/s, compared to 2.8 rad/s of geometric methods.

This paper introduces a pair of low-cost, light-weight and compliant force-sensing gripping pads used for manipulating box-like objects with smaller-sized humanoid robots. These pads measure normal gripping forces and center of pressure (CoP). A calibration method is developed to improve the CoP measurement accuracy. A hybrid force-alignment-position control framework is proposed to regulate the gripping forces and to ensure the surface alignment between the grippers and the object. Limit surface theory is incorporated as a contact friction modeling approach to determine the magnitude of gripping forces for slippage avoidance. The integrated hardware and software system is demonstrated with a NAO humanoid robot. Experiments show the effectiveness of the overall approach.

Randomized trials are widely considered as the gold standard for evaluating the effects of decision policies. Trial data is, however, drawn from a population which may differ from the intended target population and this raises a problem of external validity (aka. generalizability). In this paper we seek to use trial data to draw valid inferences about the outcome of a policy on the target population. Additional covariate data from the target population is used to model the sampling of individuals in the trial study. We develop a method that yields certifiably valid trial-based policy evaluations under any specified range of model miscalibrations. The method is nonparametric and the validity is assured even with finite samples. The certified policy evaluations are illustrated using both simulated and real data.

We consider the problem of evaluating the performance of a decision policy using past observational data. The outcome of a policy is measured in terms of a loss (aka. disutility or negative reward) and the main problem is making valid inferences about its out-of-sample loss when the past data was observed under a different and possibly unknown policy. Using a sample-splitting method, we show that it is possible to draw such inferences with finite-sample coverage guarantees about the entire loss distribution, rather than just its mean. Importantly, the method takes into account model misspecifications of the past policy - including unmeasured confounding. The evaluation method can be used to certify the performance of a policy using observational data under a specified range of credible model assumptions.