A decoupled Bayesian method for snake robot control in unstructured environment

This paper presents a method which avoids the common practice of using a complex coupled snake robot model and performing kinematic analysis for control in cluttered environments. Instead, we introduce a completely decoupled dynamical Bayesian formulation with respect to interacted snake robot links and environmental objects, which requires much lower complexity for efficient and robust control. When a snake robot does not interact with obstacles, it runs by a simple serpenoid controller. However, when it exhibits interaction with environments, defined as close proximity or collision with targets and/or obstacles, we extend the conventional Bayesian framework by modeling such interactions in terms of stimuli. The proposed 'multi-neural-stimulus function' represents the cumulative effect of both external environmental influences and internal constraints of the snake robot. It implicitly handles the 'unexpected collision' problem and thus solve the difficult data association and shape adjustment problems for snake robot control in an innovative way. Preliminary experimental results have demonstrated promising performance of the proposed method comparing with the state-of-the-art.

Counterfactual learning in enhancing resilience in autonomous agent systems

Resilience in autonomous agent systems is about having the capacity to anticipate, respond to, adapt to, and recover from adverse and dynamic conditions in complex environments. It is associated with the intelligence possessed by the agents to preserve the functionality or to minimize the impact on functionality through a transformation, reconfiguration, or expansion performed across the system. Enhancing the resilience of systems could pave way toward higher autonomy allowing them to tackle intricate dynamic problems. The state-of-the-art systems have mostly focussed on improving the redundancy of the system, adopting decentralized control architectures, and utilizing distributed sensing capabilities. While machine learning approaches for efficient distribution and allocation of skills and tasks have enhanced the potential of these systems, they are still limited when presented with dynamic environments. To move beyond the current limitations, this paper advocates incorporating counterfactual learning models for agents to enable them with the ability to predict possible future conditions and adjust their behavior. Counterfactual learning is a topic that has recently been gaining attention as a model-agnostic and post-hoc technique to improve explainability in machine learning models. Using counterfactual causality can also help gain insights into unforeseen circumstances and make inferences about the probability of desired outcomes. We propose that this can be used in agent systems as a means to guide and prepare them to cope with unanticipated environmental conditions. This supplementary support for adaptation can enable the design of more intelligent and complex autonomous agent systems to address the multifaceted characteristics of real-world problem domains.

Optimal planar leg geometry in robots and crabs for idealized rocky terrain

Natural terrain is uneven so it may be beneficial to grasp onto the depressions or 'valleys' between obstacles when walking over such a surface. To examine how leg geometry influences walking across obstacles with valleys, we (1) modeled the performance of a two-linkage leg with parallel axis 'hip' and 'knee' joints to determine how relative segment lengths influence stepping across rocks of varying diameter, and (2) measured the walking limbs in two species of intertidal crabs,Hemigrapsus nudusandPachygrapsus crassipes, which live on rocky shores and granular terrains. We idealized uneven terrains as adjacent rigid hemispherical 'rocks' with valleys between them and calculated kinematic factors such as workspace, limb angles with respect to the ground, and body configurations needed to step over rocks. We first find that the simulated foot tip radius relative to the rock radius is limited by friction and material failure. To enable force closure for grasping, and assuming that friction coefficients above 0.5 are unrealistic, the foot tip radius must be at least 10 times smaller than that of the rocks. However, ratios above 15 are at risk of fracture. Second, we find the theoretical optimal leg geometry for robots is, with the distal segment 0.63 of the total length, which enables the traversal of rocks with a diameter that is 37% of the total leg length. Surprisingly, the intertidal crabs' walking limbs cluster around the same limb ratio of 0.63, showing deviations for limbs less specialized for walking. Our results can be applied broadly when designing segment lengths and foot shapes for legged robots on uneven terrain, as demonstrated here using a hexapod crab-inspired robot. Furthermore, these findings can inform our understanding of the evolutionary patterns in leg anatomy associated with adapting to rocky terrain.

A general locomotion control framework for multi-legged locomotors

Serially connected robots are promising candidates for performing tasks in confined spaces such as search and rescue in large-scale disasters. Such robots are typically limbless, and we hypothesize that the addition of limbs could improve mobility. However, a challenge in designing and controlling such devices lies in the coordination of high-dimensional redundant modules in a way that improves mobility. Here we develop a general framework to discover templates to control serially connected multi-legged robots. Specifically, we combine two approaches to build a general shape control scheme which can provide baseline patterns of self-deformation ('gaits') for effective locomotion in diverse robot morphologies. First, we take inspiration from a dimensionality reduction and a biological gait classification scheme to generate cyclic patterns of body deformation and foot lifting/lowering, which facilitate the generation of arbitrary substrate contact patterns. Second, we extend geometric mechanics, which was originally introduced to study swimming at low Reynolds numbers, to frictional environments, allowing the identification of optimal body-leg coordination in this common terradynamic regime. Our scheme allows the development of effective gaits on flat terrain with diverse numbers of limbs (4, 6, 16, and even 0 limbs) and backbone actuation. By properly coordinating the body undulation and leg placement, our framework combines the advantages of both limbless robots (modularity and narrow profile) and legged robots (mobility). Our framework can provide general control schemes for the rapid deployment of general multi-legged robots, paving the way toward machines that can traverse complex environments. In addition, we show that our framework can also offer insights into body-leg coordination in living systems, such as salamanders and centipedes, from a biomechanical perspective.

Hands to Hexapods, Wearable User Interface Design for Specifying Leg Placement for Legged Robots

Specifying leg placement is a key element for legged robot control, however current methods for specifying individual leg motions with human-robot interfaces require mental concentration and the use of both arm muscles. In this paper, a new control interface is discussed to specify leg placement for hexapod robot by using finger motions. Two mapping methods are proposed and tested with lab staff, Joint Angle Mapping (JAM) and Tip Position Mapping (TPM). The TPM method was shown to be more efficient. Then a manual controlled gait based on TPM is compared with fixed gait and camera-based autonomous gait in a Webots simulation to test the obstacle avoidance performance on 2D terrain. Number of Contacts (NOC) for each gait are recorded during the tests. The results show that both the camera-based autonomous gait and the TPM are effective methods in adjusting step size to avoid obstacles. In high obstacle density environments, TPM reduces the number of contacts to 25% of the fixed gaits, which is even better than some of the autonomous gaits with longer step size. This shows that TPM has potential in environments and situations where autonomous footfall planning fails or is unavailable. In future work, this approach can be improved by combining with haptic feedback, additional degrees of freedom and artificial intelligence.

Unified Approach to the Motion Design for a Snake Robot Negotiating Complicated Pipe Structures

A unified method for designing the motion of a snake robot negotiating complicated pipe structures is presented. Such robots moving inside pipes must deal with various “obstacles,” such as junctions, bends, diameter changes, shears, and blockages. To surmount these obstacles, we propose a method that enables the robot to adapt to multiple pipe structures in a unified way. This method also applies to motion that is necessary to pass between the inside and the outside of a pipe. We designed the target form of the snake robot using two helices connected by an arbitrary shape. This method can be applied to various obstacles by designing a part of the target form specifically for given obstacles. The robot negotiates obstacles under shift control by employing a rolling motion. Considering the slip between the robot and the pipe, the model expands the method to cover cases where two helices have different properties. We demonstrated the effectiveness of the proposed method in various experiments.

Adaptive Locomotion Control of a Hexapod Robot via Bio-Inspired Learning

In this paper, an adaptive locomotion control approach for a hexapod robot is proposed. Inspired from biological neuro control systems, a 3D two-layer artificial center pattern generator (CPG) network is adopted to generate the locomotion of the robot. The first layer of the CPG is responsible for generating several basic locomotion patterns and the functional configuration of this layer is determined through kinematics analysis. The second layer of the CPG controls the limb behavior of the robot to adapt to environment change in a specific locomotion pattern. To enable the adaptability of the limb behavior controller, a reinforcement learning (RL)-based approach is employed to tune the CPG parameters. Owing to symmetrical structure of the robot, only two parameters need to be learned iteratively. Thus, the proposed approach can be used in practice. Finally, both simulations and experiments are conducted to verify the effectiveness of the proposed control approach.

Genetic Fuzzy Based Scalable System of Distributed Robots for a Collaborative Task

This paper introduces a new genetic fuzzy based paradigm for developing scalable set of decentralized homogenous robots for a collaborative task. In this work, the number of robots in the team can be changed without any additional training. The dynamic problem considered in this work involves multiple stationary robots that are assigned with the goal of bringing a common effector, which is physically connected to each of these robots through cables, to any arbitrary target position within the workspace of the robots. The robots do not communicate with each other. This means that each robot has no explicit knowledge of the actions of the other robots in the team. At any instant, the robots only have information related to the common effector and the target. Genetic Fuzzy System (GFS) framework is used to train controllers for the robots to achieve the common goal. The same GFS model is shared among all robots. This way, we take advantage of the homogeneity of the robots to reduce the training parameters. This also provides the capability to scale to any team size without any additional training. This paper shows the effectiveness of this methodology by testing the system on an extensive set of cases involving teams with different number of robots. Although the robots are stationary, the GFS framework presented in this paper does not put any restriction on the placement of the robots. This paper describes the scalable GFS framework and its applicability across a wide set of cases involving a variety of team sizes and robot locations. We also show results in the case of moving targets.