Plane detection from depth images is a crucial subtask with broad robotic applications, often accomplished by iterative methods such as Random Sample Consensus (RANSAC). While RANSAC is a robust strategy with strong probabilistic guarantees, the ambiguity of its inlier threshold criterion makes it susceptible to false positive plane detections. This issue is particularly prevalent in complex real-world scenes, where the true number of planes is unknown and multiple planes coexist. In this paper, we aim to address this limitation by proposing a generalised framework for plane detection based on model information optimization. Building on previous works, we treat the observed depth readings as discrete random variables, with their probability distributions constrained by the ground truth planes. Various models containing different candidate plane constraints are then generated through repeated random sub-sampling to explain our observations. By incorporating the physics and noise model of the depth sensor, we can calculate the information for each model, and the model with the least information is accepted as the most likely ground truth. This information optimization process serves as an objective mechanism for determining the true number of planes and preventing false positive detections. Additionally, the quality of each detected plane can be ranked by summing the information reduction of inlier points for each plane. We validate these properties through experiments with synthetic data and find that our algorithm estimates plane parameters more accurately compared to the default Open3D RANSAC plane segmentation. Furthermore, we accelerate our algorithm by partitioning the depth map using neural network segmentation, which enhances its ability to generate more realistic plane parameters in real-world data.

Quadruped robots are able to exhibit a range of gaits, each with its own traversability and energy efficiency characteristics. By actively coordinating between gaits in different scenarios, energy-efficient and adaptive locomotion can be achieved. This study investigates the performances of learned energy-efficient policies for quadrupedal gaits under different commands. We propose a training–synthesizing framework that integrates learned gait-conditioned locomotion policies into an efficient multiskill locomotion policy. The resulting control policy achieves low-cost smooth switching and controllable gaits. Our results of the learned multiskill policy demonstrate seamless gait transitions while maintaining energy optimality across all commands.

Unmanned aerial vehicles (UAVs) for contact-based tasks at height can greatly improve the safety of the human workers involved. However, performing contact-based tasks with typical under-actuated UAVs is non-trivial. Due to their coupled translational and rotational dynamics and their limited station-keeping performance under physical disturbances, it is difficult to maintain precise and consistent contact. We address these problems in the context of physical interaction with vertical, cylindrical target objects, such as trees. We present a novel UAV design with a pair of tilt-rotors and a landing gear that can reconfigure into a front-mounted, two-fingered gripper. While the tilt-rotors provide horizontal force toward the target object without pitching the UAV forward, the reconfigurable landing gear enables the UAV to obtain support from the target object. Such support results in an approximately 80% improvement in position- and heading-keeping performance. Moreover, the landing gear is designed as a cable-driven under-actuated system, which requires only one actuator to control both the reconfiguration and the grasping (i.e., five degrees of freedom in total). Such a minimalist design helps keep the UAV power consumption for interactions low. This marks progress towards safe, high-precision physical interaction against vertical, cylindrical target objects. Our UAV in action: https://youtu.be/D-65vldox_A.

Inspired by the digital twinning systems, a novel real-time digital double framework is developed to enhance robot perception of the terrain conditions. Based on the very same physical model and motion control, this work exploits the use of such simulated digital double synchronized with a real robot to capture and extract discrepancy information between the two systems, which provides high dimensional cues in multiple physical quantities to represent differences between the modelled and the real world. Soft, non-rigid terrains cause common failures in legged locomotion, whereby visual perception solely is insufficient in estimating such physical properties of terrains. We used digital double to develop the estimation of the collapsibility, which addressed this issue through physical interactions during dynamic walking. The discrepancy in sensory measurements between the real robot and its digital double are used as input of a learning-based algorithm for terrain collapsibility analysis. Although trained only in simulation, the learned model can perform collapsibility estimation successfully in both simulation and real world. Our evaluation of results showed the generalization to different scenarios and the advantages of the digital double to reliably detect nuances in ground conditions.

In robotic tasks that require physical interactions such as manipulation and legged locomotion, it is important to simultaneously measure contact forces and contact angles. This paper presents a unified solution for simultaneously measuring three axis contact forces and contact angles for legged locomotion or manipulation. Unlike most tactile sensors, the presented design utilizes the stress field method by sampling pressures over multiple locations within an elastomer, enabling inherently robust operation against impact and abrasive interactions. The presented sensor is designed for point-feet quadrupedal robots and can be easily scaled down for other applications such as grasping. The sampled stress distribution is mapped to output forces fx, fy, and fzand two contact angles, θ and ψ on the hemispherical sensor surface via Gaussian process regression. The prototype sensor is able track normal and shear forces accurately, achieving a normalized root mean (RMS) squared error of only 1.00% - 1.36% for fzacross multiple tests with up to 180N normal force, and a normalized RMS error of 1.71% - 4.67% and 1.82% - 6.68% for fxand fy, respectively, with up to 80N shear force. Additionally, the footpad is able to estimate the contact location coordinates θ and ψ with a normalized RMS error of 2.69% -7.51% over a range of 0-40° and 2.79% - 9.62% over a range of 0-30°, respectively. The footpad can estimate contact location over a maximum range of θ = ±45° and ψ = ±45°, and can withstand over 450N of normal force at location θ = ψ = 0° without reaching saturation. This prototype demonstrates the ability to simultaneously measure force in three axes and contact angles using Gaussian process regression, with the potential to explore other regression methods for embedded computing and miniaturization of the design for finger tip scale sensors.

This paper exemplifies the design process for legged machines capable of dynamic behaviors. In order to achieve high performance robots, it is crucial to guarantee harmonious integration between software and hardware. Hence, the development of such capable robotic platforms must address design requirements that meet the assumptions of typical model-based controllers but also respect the physical limitations of a real system. First, we show that proper hardware design choices can greatly aid the control algorithm by approximating the physical robot to the template assumptions. We include actuation and sensing design examples that allows a simple model to capture a major portion of the natural dynamic behavior of the physical machine. Results are applied to a real robot (Figure 1) and we show that the adopted methodology is able to address typical problems in legged robots such as high bandwidth force control and robustness to impact. Finally, a simple model-based balance controller that takes advantage of the fidelity of the template model to the real machine is implemented. These are examples of software-hardware codesign processes that vastly facilitate robotic control.

This paper presents a new approach to the characterization of tactile array sensors that aims to reduce the computational time needed for convergence to obtain a useful estimator for normal and shear forces. This is achieved by breaking up the sensor characterization into two parts: a linear regression portion using multivariate least squares regression, and a nonlinear regression portion using a neural network as a multi-input, multi-output function approximator. This procedure has been termed Least Squares Artificial Neural Network (LSANN). By applying LSANN on the 2nd generation MIT Cheetah footpad, the convergence speed for the estimator of the normal and shear forces is improved by 59.2% compared to using only the neural network alone. The normalized root mean squared error between the two methods are nearly identical at 1.17% in the normal direction, and 8.30% and 10.14% in the shear directions. This approach could have broader implications in greatly reducing the amount of time needed to train a contact force estimator for a large number of tactile sensor arrays (i.e. in robotic hands and skin).

In this paper we examine the dynamics of a unique type of jet propelled, spheroidal robot design. This robot uses jets angled inward into a diamond shape to achieve superior planar dynamics. We explore the role of the diamond configuration in avoiding nonminimum phase behavior and we examine the best vehicle aspect ratios for this type of robot design. We use a degree of controllability metric to illustrate the uncontrollable behavior of certain designs and also identify an optimal aspect ratio of 1.4. The paper concludes by incorporating these lessons into a new 5 degree-of-freedom prototype robot that provides substantial improvements over previous designs. This robot uses centrifugal pumps and fluidic valves to achieve high maneuverability and unique motions such as forward and reverse motions, sway translations, and turning in place. In addition, this design can achieve improved forward efficiency through the use of dual output-pumps and can perform these planar motions at various vehicle depths through the use of a closed loop depth control system.

This paper introduces a bounding gait control algorithm that allows a successful implementation of duty cycle modulation in the MIT Cheetah 2. Instead of controlling leg stiffness to emulate a ‘springy leg’ inspired from the Spring-Loaded-Inverted-Pendulum (SLIP) model, the algorithm prescribes vertical impulse by generating scaled ground reaction forces at each step to achieve the desired stance and total stride duration. Therefore, we can control the duty cycle: the percentage of the stance phase over the entire cycle. By prescribing the required vertical impulse of the ground reaction force at each step, the algorithm can adapt to variable duty cycles attributed to variations in running speed. Following linear momentum conservation law, in order to achieve a limit-cycle gait, the sum of all vertical ground reaction forces must match vertical momentum created by gravity during a cycle. In addition, we added a virtual compliance control in the vertical direction to enhance stability. The stiffness of the virtual compliance is selected based on the eigenvalue analysis of the linearized Poincaré map and the chosen stiffness is 700 N/m, which corresponds to around 12% of the stiffness used in the previous trotting experiments of the MIT Cheetah, where the ground reaction forces are purely caused by the impedance controller with equilibrium point trajectories. This indicates that the virtual compliance control does not significantly contributes to generating ground reaction forces, but to stability. The experimental results show that the algorithm successfully prescribes the duty cycle for stable bounding gaits. This new approach can shed a light on variable speed running control algorithm.

In this paper, we introduce the design principles for highly efficient legged robots and the implementation of the principles on the MIT Cheetah robot. Three major energy loss modes during locomotion are heat losses through the actuators, losses through the transmission, and the interaction losses that includes all losses of the system interacting with the environment. We propose four design principles that minimize these losses: employment of high torque density motors, low impedance transmission, energy regenerative electronics and a design architecture that minimizes the leg inertia. We present the design features of the MIT cheetah robot as an embodiment of these principles. The resulting cost of transport (COT) is 0.51 during 2.3 m/s running, which rivals running animals in the same scale.

This paper illustrates the fabrication and characterization of a footpad based on an original principle of volumetric displacement sensing. It is intended for use in detecting ground contact forces in a running quadrupedal robot. The footpad is manufactured as a monolithic, composite structure composed of multi-graded polymers which are reinforced by glass fiber to increase durability and traction. The volumetric displacement sensing principle utilizes a hyperelastic gel-like pad with embedded magnets that are tracked with Hall-effect sensors. Normal and shear forces can be detected as contact with the ground which causes the gel-like pad to deform into rigid wells. This is all done without the need to expose the sensor. A one-time training process using an artificial neural network was used to relate the normal and shear forces with the volumetric displacement sensor output. The sensor was shown to predict normal forces in the Z-axis up to 80N with a root mean squared error of 6.04% as well as the onset of shear in the X and Y-axis. This demonstrates a proof-of-concept for a more robust footpad sensor suitable for use in all outdoor conditions.