Huthaifa Ahmad

Mobility in daily unstructured environments, particularly in human-centered scenarios, remains a fundamental challenge for mobile robots. While traditional prediction-based approaches primarily estimate partial features for robot decision making, such as position and velocity, recent world models enable direct prediction of future sensory data. However, their potentials in human-inclusive environments remain underexplored. To assess the feasibility of world models in facilitating human-robot interactions, we propose a robot framework using a deep generative model that jointly predicts multiple future observations and actions. Our approach leverages first-person-view (FPV) raw sensor data, integrating both observations and actions to enhance predictive capabilities in dynamic human-populated settings. Experimental results demonstrate that our method is capable of generating a range of candidate futures for one condition and planning actions based on observation guidance. These findings highlight the potential of our approach for facilitating autonomous robots’ coexistence with human.

Recent advancements in deep learning and large-scale language models have driven interest in creating conversational robots capable of heartful interactions with humans. However, most existing systems are tailored for specific contexts and lack a comprehensive framework to assist humans in daily activities. Developing a fully autonomous robot that can operate alongside humans and interact with them in dynamic environments is a complex task that requires addressing particular software and hardware demands. These demands often conflict, resulting in trade-offs based on the intended application. To overcome this challenge, we propose a body design that leverages passive dynamics. We illustrate how the essential devices for computation, sensing, and actuation can be integrated into the robot without compromising its embodiment requirements. Conversely, we utilize the weight and placement of these devices to achieve the physical characteristics needed for a robotic body that is well-suited for coexistence with humans. We validate this approach through the development of Indy, a mobile communication robot platform designed to coexist with humans. The employed mechanisms enable Indy to maintain an upright posture without active control and ensure safe physical interactions. Experimental results indicate that the generated body movement positively impacts users’ perceptions, promoting a sense of anthropomorphism and enhancing the interaction experience. This confirms that the selected design approach not only provides mechanical advantages but also improves the natural appearance of the robot’s movements.

This paper investigates the influence of adding an upper body to a bipedal robot on its stable walking behavior. The robot’s parts are mutually interconnected through an actuator network system. Therefore, the movement pattern of the upper body depends on the type of interactions created with other limbs. Throughout the experiments, various interactions among the different body parts were tested. The results showed that a robot with a motionless upper body exhibited unstable walking behavior. However, once the same upper body was involved and interacted properly, with other body parts, its movement significantly helped to stabilize the behavior of the robot.

In diverse situations, humans produce natural and adaptable bipedal locomotion by cooperatively manipulating the interactions among the different parts of their bodies and the environment. Therefore, to realize a robot with adaptable behavior, it should be enabled to adjust its morphology accordingly in response to environmental changes. From this perspective, this study introduces the development of a bipedal robot with adaptive morphology. By implementing an actuator network system (ANS), the robot is able to manipulate the physical characteristics of its legs and the way they interact with each other. Two experiments have been conducted: main and supplementary experiments. The main experiment examined how effective is adjusting the robot’s morphology on changing the robot’s behavior. The experiment was conducted on different ground materials and under different connection patterns between the robot’s legs. During the experiment, the robot’s behavior was evaluated in reference to four aspects: walking style, stability, speed, and moving direction. The supplementary experiment took the results of the main experiment and used it to improve the robot’s behavior during locomotion. The robot was enabled to automatically switch between the different connection patterns of the ANS, which in turn changed the interaction between the robot’s legs and generated a more suitable dynamics for the surrounding environment.

Realizing adaptability to environmental changes requires the robot’s body to change according to the environment. From this perspective, several studies have considered variable compliant actuation to change the physical characteristics of the robot as it interacts with the environment. Robots with this ability show a variety of efficient stable motions during contact with the environment. However, having locally variable compliant parts with independent dynamics under the same body may be insufficient for achieving adaptability in diverse environments. To extend the idea of variable compliant actuation, from being used locally to the level of the entire body’s dynamics, in this study, we use an actuator network system (ANS). As an approximation of bipedal robots, we developed an eight-legged rimless wheel robot with an ANS that allows energy transfer among limbs through passive interactions among mutually interconnected air cylinders mounted on the robot’s legs. We experimentally demonstrated that by using the ANS to realize energy transfer among limbs, the robot performance improved.