Like 17 million people worldwide, an individual with cerebral palsy (CP) does not have the opportunity to walk harmoniously in society due to long-life impairments in movement and posture. The natural course of CP can be modulated by treatments and therapies that are nowadays mostly decided on the basis of assessments performed in clinical settings. The Clinical Gait Analysis (CGA) consists of a set of instrumented assessments aiming to obtain precise and quantitative information about a patient’s gait deviations, in order to better identify his motor disorders and their possible causes. However, it is not clear whether gait assessments in clinics (‘capacity’) are representative of daily-life behaviors (‘performance’). In this context, the present thesis aimed at exploring the gap between gait assessed in the laboratory and in real life for children with CP, as compared to children with typical development (TD). Two main objectives were settled: (i) to propose an objective and validated tool for gait assessments in a daily-life context with the highest possible accuracy as compared to clinical standard references; and (ii) to compare gait characteristics between both environments, the laboratory and the real life. Considering the immense progress in the design of wearable sensors, notably inertial measurement units (IMU), great enthusiasm recently arose for their use in ambulatory monitoring. IMUs, including 3D accelerometers and gyroscopes, were thus exploited in this work as a solution to measure gait features in the children’s daily life. A comparative study was first carried out to determine the most appropriate wearable system to be used for children with CP and for long-term measurements. Sensors located on the shanks and thighs and associated algorithms revealed to be the best solution. Next, a proof-of-concept study was completed and emphasized the need for personalized data processing for children with CP but also with TD. The second part (ii), dealing with the comparisons of walking capacity versus performance, adopted a progressive approach. The first step was the comparison between standardized walking, i.e. during a CGA protocol, and walking under challenging situations, such as dual tasks, i.e. thinking and talking while walking, in the laboratory. We found that dual tasks were responsible for lower motor gait capacities. The next step was the effective comparison of gait characteristics measured in the laboratory with the same gait characteristics measured in real-life settings, using the previously determined wearable system. First, walking speed, a global indicator of gait, and second, multiple gait parameters were compared between laboratory and daily life. Through two studies, we evidenced that children with CP have highly heterogenous behaviors but tend to perform better in clinical settings. Besides, we have highlighted that capacity is associated with performance in children with CP when they are evaluated with the same metrics. Through this doctoral work, the great challenges of using IMUs for gait analysis of children with CP have been highlighted. The proposed solutions reached a compromise between accuracy, number of outcomes, and acceptance. Furthermore, the presented clinical results proved with objective and quantitative evidence the existence of a gap between gait assessed in the laboratory and gait in real life, which could help clinicians to devise therapeutic plans better tailored to each child’s needs.