CERBERUS ©
MUM-T
PLATFORM
MUM-T Digital Platform
Deep Reasoning & Planning AiGENTS
Our Manned-Unmanned-Teaming digital platform increases autonomous systems efficiency while operating as a team with or without humans in the loop. Our entire MUM-T digital platform is developed 100% in house meaning no 3rd party IP and/or royalties.
Our SA&U AiGENTs handle real-life complex decision processes under uncertainty, including partial information and noisy observations.
Our deep-planning AiGENTs are capable to construct and execute plans for very complex manned-unmanned-teaming missions, using low latency deep-planning algorithms.
To meet full autonomy and support complex real-life mission-critical tasks we use a unique combination of model-free deep-reinforcement-learning and model-based planning. Both require fast and accurate real-life digital-twin simulators. Our Trained-By-Simulator and Sim-2-Real-Simulator support acceleration of more than 1000X, enable cost effective training of multi-agent systems with reduced time-to-market and low-latency real-time planning.
Last, understanding our customers needs, we provide an “explainable AI” solution which handles both UAVs and UGVs simultaneously to meet a mutual common goal for all platforms.
Complex Missions
Hierarchical Planning
Low Latency
Deep Planning
Combining:
-
Statistical approaches to model human brain function (e.g. the cognitive abilities based on statistical principles).
-
Strong CPUs/GPUs, large memory pools.
-
Knowledge graphs & deep-RL algorithms.
our AiGENTs excel at any task.
Meeting human expert standards, AiGENT-TECH hierarchical planning engine learns and adapts based on experience.
Hierarchical planning, which mimic the human brain decision making process, are designed to function in real-life scenarios.
Like humans, hierarchical planning systems should function under uncertainty, ambiguity, partial observation, dynamic environment and sometime even under wrong perception inputs (the most challenging cases).
In order to succeed in their missions, with high probability, these systems should:
-
Actively learn on-line as information changes, and as goals and requirements evolve.
-
Remember previous interactions, in order to increase future success rates (learning based on experience).
-
Resolve ambiguity, tolerate uncertainty and wrong observations.
-
Interact with the surrounding environment (sensing) and with their end-users so that those users can define their needs.
-
Assist in 'defining the problem' by asking questions or finding additional input sources if a problem statement is ambiguous or incomplete.
-
Seamless integration with your existing IT platforms
-
Features tailored for your needs
-
24/7 support
Minimal Evidences
Situation Awarness
DEEP REASONING & SITUATION AWARENESS
Situation awareness & understanding is the ability to estimate and predict a possible situation involving multiple actors and/or objects in different locations, in which actors may trigger events or activities occurring over time, and where the meaning of the situation is revealed by integrating previous knowledge with evidence from multiple sources.
We combine knowledge-graphs, probabilistic modeling, Bayesian inference and model based deep reinforcement learning framework to provide our customers "better than human" situation awareness & understanding solutions.
