Oscorp Energy

Basic Information

Applicant Type: Organisation

Organisation Name: Oscorp Energy

Main Questions

Problem Solution

A. THE PROBLEM:
Australia is facing a flood of end-of-life lithium-ion batteries. EV uptake and gadget turnover are driving volumes sky-high, yet 90 % of small batteries end up in landfill (CSIRO). These batteries arrive at kerbside trucks, MRFs and metal yards in every size and chemistry imaginable, but operators have no reliable way to separate them safely.

The result is both unsafe and uneconomic:
1. Fire risk: Industry surveys (ACOR) show roughly 12 000 battery-sparked fires or thermal events each year - about five incidents per site - costing the average recycler $417k in damage, downtime and soaring insurance premiums.
2. Lost value: Mixed or misidentified batteries clog downstream plants, cut metal recovery rates and send critical minerals to landfill.

Why today’s sorting systems fail
a. Manual pick-lines: Operators can’t tell similar chemistries apart (e.g., NMC vs LFP 18650 cells), can’t keep up with the growing mix of shapes and embedded packs, and can’t spot hidden faults like swelling or hot-spots. The job is labour-heavy, error-prone and impossible to scale.
b. Automated MRF lines: Standard optical or magnetic sorters are tuned for ferrous/non-ferrous splits. Magnets miss most batteries; low-resolution sensors can’t read chemistry or damage state. Throughput is high but selectivity is crude, so dangerous and low-grade cells slip through, contaminating bales and fuelling more fires.

Bottom line: Australia needs a smarter, high-precision way to sort lithium-ion batteries—one that makes recycling both safe and profitable.

B. THE SOLUTION
Oscorp Energy’s Autonomous (not automated) Sorting Technology is a modular, AI-driven conveyor and robotic system that performs real-time classification and diversion of loose and embedded batteries at industrial scale.

a. For Battery Recyclers
- Chemistry-grade sorting. Multi-spectrum “fingerprinting” tags chemistry and form factor with highest accuracy, lifting black-mass purity and unlocking more recovered value of black mass.
- Thermal-risk detection. Real-time thermography screens flag swollen or hot cells, removing hazards before shredding.
- Adaptive learning & reporting. LUIGI™ (our AI model) retrains on your feed, tightening accuracy each shift while auto-generating mass-balance and ESG dashboards.
- Productivity economics. Throughput is 10× manual speed with ~90 % labour cost reduction, making high-precision sorting commercially attractive even at sub-tonne volumes.

b. For Mixed-Waste MRFs
- Inline battery detection. Computer vision + thermography + metal sensing plucks loose or embedded batteries before shredders, cutting fire incidents by up to 95%.
- Drop-in retrofit. Mounts onto existing conveyors with 24-48 h downtime - no major rebuild required.
- Continuous compliance. Non-stop scanning keeps pace with peak loads, meeting tighter hazardous-waste rules and helping lower insurance premiums.
- Modular placement. Pre-sort or critical-point configurations shield your most fire-prone zones and scale as volumes rise.

Bottom line: Oscorp’s autonomous platform lets recyclers recover more metals, enables MRFs to run safer, fire-resilient lines, and drives a circular, low-risk battery economy for Queensland.

Impact

Oscorp Energy’s autonomous sorting platform delivers the first Queensland-built, AI-guided “front door” for lithium-ion battery recycling and MRFs. By fusing multi-sensor imaging, the system makes millisecond decisions on every cell and can clip straight into either a specialist recycler or a mixed-waste MRF - no major line rebuild required. This jump from basic automation to true autonomy unlocks five strategic wins for the state.

1. Safety & business continuity: Up-stream ejection of damaged or embedded batteries is expected to cut ignition events in QLD facilities by >80 %, tackling the 200+ battery fires recorded in the past 12 months. Fewer evacuations and cleaner air for local communities; lower premiums and downtime for operators.
2. Resource recovery targets: Chemistry-pure streams lift hydrometallurgical yields by ~20 %, helping meet the state’s 65 % recycling / 80 % waste-recovery goals for 2030. Aligns directly with the Queensland Waste Management & Resource Recovery Strategy and its 75 % long-term recycling ambition.
3. Economic value & jobs: Each line replaces labour-intensive pick stations and supports ~5 to 15 skilled positions in robotics, AI support and field service; a ten-site rollout would create ~150 enduring roles. Diversifies regional employment and builds a local advanced-manufacturing supply chain around conveyors, sensors and control software.
4. Critical-minerals sovereignty: Higher-purity black mass captures cobalt, nickel and lithium, feeding emerging cathode projects at Townsville and Gladstone. Keeps strategic metals in-state, strengthening Queensland’s battery-materials ecosystem and export potential.
5. Leverage of government funding: The technology is “shovel-ready” for the $45m Recycling & Jobs Fund stream targeting battery waste; capital co-investment accelerates capacity without new levies. Turns public grants into bankable infrastructure that lowers whole-of-system recycling costs.

Broader community co-benefits
- Cleaner, safer kerbside services: Councils can now accept any battery chemistry with confidence, complementing the state’s plan to expand drop-off points.
- Environmental protection: Diverting toxic metals from landfill reduces leachate risks to reef-catchment waterways and cuts embodied-carbon emissions tied to virgin mining.

Bottom line: Oscorp Energy transforms Queensland’s battery-fire headache into a circular-economy asset - advancing state recycling targets, safeguarding workers and neighbourhoods, and anchoring new high-tech jobs in the Sunshine State.

Business Model

Oscorp Energy is a headquartered in regional NSW, seed-stage cleantech AI and hardware company that designs, builds and services AI-powered battery-sorting equipment (currently TRL 3.5 moving to TRL 5). The team is three FTE covering ML, robotics, mechanical design and field service

A. How we make money

We run two complementary revenue streams:
1. Turnkey sales – Full-system purchase with onboarding and integration. One-time setup fee + optional support package. Ideal for recyclers wanting full control and ownership

2. Machine-as-a-Service (MaaS) – MRFs and smaller operators avoid capex and simply pay around $0.05-0.10c per kilo processed. Includes installation, ongoing support, and AIpowered updates. No upfront CAPEX required by the customer expect for installation and transport.

Both models layer on recurring data and predictive-maintenance services fed by the system’s sensor telemetry.

Launch (GTM) plan: one battery-recycler lane on a turnkey basis and one lane at a mixed-waste MRF - both already in discussion (one MRF in NSW locked in).

Why it works for Queensland

The capex-free MaaS option lets regional MRFs eliminate battery fires without new borrowing, while turnkey buyers maximise black-mass purity and ROI. Every installed lane boosts safety, keeps critical minerals in-state and generates lifelong service revenue—creating a sustainable, high-tech recycling ecosystem for Queensland.

Market Readiness

Our autonomous sorting system currently sits at TRL 3.5: the core sensing architecture and control software have been proven in the lab, and the first generation of AI classification models is under active training. A provisional patent covering the multi-sensor fusion and control logic has already been filed, locking in early IP.

Pilots to date and in the pipeline
We have not yet installed hardware on a live waste line, but we have secured a Phase 1 pilot with a large NSW MRF that handles ~100 000 t yr-¹ of mixed yellow-bin waste. Sensor rigs will be mounted over an existing belt this July to collect in-situ data, validate chemistry-detection accuracy, and fine-tune our models. In parallel, we are in final talks with one of Australia’s largest dedicated battery recyclers and hold a letter of interest from the UK’s leading recycler—both slated to follow the same phased approach.

Testing still required before commercial launch
- Phase 1 (data-capture & model tuning): Sensors only, no ejectors, run for ~8 weeks to stress-test detection under real throughput.
- Phase 2 (full hardware integration): Install conveyors, diverters and edge GPUs for end-to-end trials. This stage will run 12–24 weeks, giving us at least three months of continuous, production-rate operation across two distinct waste streams (mixed municipal and battery-only). Insights from both environments will harden the AI against edge cases and prove mechanical reliability.

Timeframes & logistics
-Notice to mobilise a pilot: we need four to six weeks after a site agreement is signed to fabricate mounts, ship sensors and deploy the team.
-Duration of each pilot: Phase 1 ≈ 8 weeks; Phase 2 a further 12–24 weeks depending on throughput targets.
- Path to commercial launch: with a combined pilot window of 24–38 weeks (roughly six to nine months), we expect to declare the system market-ready immediately after Phase 2 closes—positioning us to take first customer orders inside the following quarter.

By running pilots in both a high-volume MRF and a specialist battery-recycling line, we will expose the AI to the full spectrum of chemistries, form factors and contamination scenarios. That diversity is critical to delivering a robust, commercially viable product that scales confidently across Queensland and beyond.

Team

1. Ani Goswami: Ani's background is Simulation Modelling & Informatics (master's degree) in the health & climate tech sectors. He is also a researcher in Battery Technology with his research focused on wirelessly discharging batteries on an industrial scale. He has led multi-million dollars projects in the past with solid product and project management skills. He is the Founder and CEO at Oscorp and also the Product Lead.

2. Dr Chandrakant Bothe: Dr Bothe holds a MS in Robotics and PhD in Artificial Intelligence (human-robot interaction). He has built and contributed significantly foundational AI models and robotics in the past successfully in Europe.

3. Dhiren Rami: Dhiren has a background in Electrical Engineering. He brings significant experience in Industrial Automation including recycling facilities' automation. He has successfully run his industrial automation contracting business in NSW.